© 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. 7458
    Prev
    Next
    INDEX
    Explanations

    superlatives and words indicating a count or quantity

    oai_token-act-pair · gemini-2.0-flash

    punctuation and conjunctions

    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
    UnknownFieldSet
    -0.85
    цездатний
    -0.84
     AssemblyCulture
    -0.84
    yntaxException
    -0.84
    principalColumn
    -0.82
     unknownFields
    -0.81
    tanleria
    -0.77
    UnusedPrivate
    -0.76
     &___
    -0.75
     <>",
    -0.75
    POSITIVE LOGITS
    !
    0.63
    .
    0.60
     throughout
    0.58
    ;
    0.58
    ,
    0.58
     for
    0.58
     from
    0.56
     because
    0.52
     within
    0.48
     since
    0.48
    Activations Density 3.242%

    No Known Activations