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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10179
    Prev
    Next
    INDEX
    Explanations

    abstract nouns or situations

    oai_token-act-pair · gemini-2.0-flash

    say "where"

    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
     nahilalakip
    -0.64
    Искәрмәләр
    -0.60
     ProtoMessage
    -0.57
    Примечания
    -0.53
     Réponses
    -0.53
    EndGlobalSection
    -0.51
    webElementXpaths
    -0.50
    Quién
    -0.50
    曖昧さ回避
    -0.49
    Referanser
    -0.49
    POSITIVE LOGITS
     where
    2.50
    where
    2.02
    Where
    1.70
     Where
    1.70
     où
    1.68
     donde
    1.66
     WHERE
    1.63
     где
    1.52
    WHERE
    1.43
     waar
    1.32
    Activations Density 1.558%

    No Known Activations