© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1432
    Prev
    Next
    INDEX
    Explanations

    passages that discuss potential improvements

    oai_token-act-pair · gemini-2.0-flash

    improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    posedge
    -0.57
    SourceChecksum
    -0.55
    deal
    -0.52
     consultato
    -0.51
    bootstrapcdn
    -0.48
     utafitiHapana
    -0.48
     beginnetje
    -0.47
    ksis
    -0.47
    ThroughAttribute
    -0.47
    liess
    -0.47
    POSITIVE LOGITS
     Meksiku
    0.53
    ześnie
    0.52
    formaz
    0.52
    Lähteet
    0.52
     nahilalakip
    0.51
     idéale
    0.49
    yargs
    0.49
     fusca
    0.48
    msgSender
    0.48
     paroisse
    0.47
    Activations Density 2.270%

    No Known Activations