© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5525
    Prev
    Next
    INDEX
    Explanations

    dates, locations, and quotes from people

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns and article snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    weichen
    -0.44
    écrire
    -0.42
     tunes
    -0.39
     noop
    -0.39
    lie
    -0.39
     Musician
    -0.37
     Painter
    -0.37
    பு
    -0.37
     Vals
    -0.36
    WriteString
    -0.36
    POSITIVE LOGITS
     disambiguazione
    0.79
    ValueStyle
    0.66
    醐
    0.64
     تضيفلها
    0.63
     defaultstate
    0.62
    WebVitals
    0.57
     autorytatywna
    0.56
    存于互联网档案馆
    0.55
    Geplaatst
    0.53
    CloseOperation
    0.53
    Activations Density 9.588%

    No Known Activations