© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5151
    Prev
    Next
    INDEX
    Explanations

    the string "lac" and words related to trials or legal actions

    oai_token-act-pair · gemini-2.0-flash

    instances of the term 'LAC' and related identifiers

    np_token-act-pair-logits · gpt-4o-mini

    No pattern could be determined. Lac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    олові
    -0.54
    scriptcase
    -0.48
    taminophen
    -0.47
     neceff
    -0.47
     propOrder
    -0.47
     Suom
    -0.46
     ninjago
    -0.45
    orph
    -0.44
    เร็
    -0.44
    isbury
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.64
    InitVars
    0.59
    EDEFAULT
    0.55
     Mu
    0.54
    Gweler
    0.54
     ModelExpression
    0.53
     unknownFields
    0.53
    Mu
    0.52
    EndInit
    0.52
    Diwedd
    0.52
    Activations Density 0.207%

    No Known Activations