© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4818
    Prev
    Next
    INDEX
    Explanations

    the word "selection"

    oai_token-act-pair · gemini-2.0-flash

    selection/select

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     Arrondissement
    -0.65
    tagHelperRunner
    -0.59
    }{*}{}
    -0.54
    TypedDataSet
    -0.54
    ?}",
    -0.54
    jspx
    -0.52
    ArgsConstructor
    -0.51
    migrationBuilder
    -0.50
     ProtoMessage
    -0.50
    databind
    -0.49
    POSITIVE LOGITS
    /**
    0.55
    mbg
    0.53
    StartTag
    0.49
    Cyfeiriadau
    0.49
    </tfoot>
    0.47
    cmath
    0.47
    Géographie
    0.47
    schild
    0.47
     vao
    0.47
     behö
    0.46
    Activations Density 0.469%

    No Known Activations