© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3352
    Prev
    Next
    INDEX
    Explanations

    non-English language text or code

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or formatting

    np_token-act-pair-logits · gpt-4o-mini

    non-English text

    np_max-act-logits · gemini-2.0-flash

    prepositions

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     safe
    -0.48
     pfalz
    -0.45
     sibi
    -0.44
     fusca
    -0.44
     acrylique
    -0.44
     carried
    -0.44
     Sosten
    -0.43
     wide
    -0.43
     rossa
    -0.41
    ManagedBean
    -0.41
    POSITIVE LOGITS
    uxxxx
    0.88
     disambiguazione
    0.68
     Picchu
    0.68
    tagHelperRunner
    0.66
    Personendaten
    0.65
    endrait
    0.64
    spreis
    0.63
    HostException
    0.63
     initComponents
    0.62
    TargetException
    0.62
    Activations Density 0.364%

    No Known Activations