© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    names of people and titles, especially those related to Edo State

    oai_token-act-pair · gemini-2.0-flash

    Nigeria/Africa locations

    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
    fatti
    -0.46
    intah
    -0.40
    >",
    -0.40
    let
    -0.39
    VertexArray
    -0.38
    มอ
    -0.38
    inkov
    -0.38
    meiras
    -0.38
    tidase
    -0.37
     Seligman
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    1.04
    ">//
    0.86
    NUMX
    0.73
    IntoConstraints
    0.69
    ագրություններ
    0.69
     AssemblyCulture
    0.68
     незавершена
    0.68
    IndentedString
    0.67
    MLLoader
    0.67
    solids
    0.66
    Activations Density 0.862%

    No Known Activations