© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8526
    Prev
    Next
    INDEX
    Explanations

    the word "mud" and words related to something being placed upon or applied to something else

    oai_token-act-pair · gemini-2.0-flash

    mud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.45
     itſelf
    -0.70
     faſt
    -0.67
     ſta
    -0.63
     raiſ
    -0.61
     uſed
    -0.61
     auffi
    -0.60
     myſelf
    -0.60
     ſp
    -0.58
     uſ
    -0.58
    POSITIVE LOGITS
    addCriterion
    0.70
    Jeografia
    0.68
     HasFactory
    0.65
    @[+][
    0.63
     TestBed
    0.63
    ValueGenerated
    0.63
     referenties
    0.62
    EndContext
    0.61
    elemField
    0.61
    -------
    0.59
    Activations Density 1.359%

    No Known Activations