© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3349
    Prev
    Next
    INDEX
    Explanations

    clauses stating judgements, conditions or conclusions

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ویکی‌پدیای
    -0.57
    Erreferentziak
    -0.56
    asses
    -0.56
    Filmografie
    -0.53
     fe
    -0.52
    ContentLoaded
    -0.52
    lorette
    -0.50
    новништво
    -0.50
    ppuden
    -0.50
    nodoc
    -0.49
    POSITIVE LOGITS
     BrowserModule
    0.63
     prossimo
    0.61
    IonicModule
    0.60
    AutoresizingMask
    0.54
     espressione
    0.53
    parsedMessage
    0.52
     réputation
    0.52
     bakgrund
    0.52
     varandra
    0.52
     politiques
    0.51
    Activations Density 3.662%

    No Known Activations