© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12816
    Prev
    Next
    INDEX
    Explanations

    personal reflections and opinions of the author

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     '{@
    -1.08
     nahilalakip
    -0.97
    RenderAtEndOf
    -0.87
    webElementXpaths
    -0.82
    KURZBESCHREIBUNG
    -0.79
    GEBURTSDATUM
    -0.78
    #+#
    -0.74
     nakalista
    -0.73
    makeConstraints
    -0.72
    TagMode
    -0.72
    POSITIVE LOGITS
     is
    1.00
     will
    0.95
     are
    0.84
     has
    0.77
     was
    0.75
     would
    0.73
     am
    0.70
     have
    0.60
    는
    0.57
    的是
    0.56
    Activations Density 2.325%

    No Known Activations