© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14980
    Prev
    Next
    INDEX
    Explanations

    mentions of past experiences, especially related to health, emotions, and conflict.

    oai_token-act-pair · gemini-2.0-flash

    Medical issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    TypedDataSet
    -0.64
    BeginInit
    -0.63
     jLabel
    -0.56
    UrlResolution
    -0.54
     LIBR
    -0.50
    libur
    -0.48
     sill
    -0.47
    andag
    -0.47
    LBL
    -0.46
     estekak
    -0.46
    POSITIVE LOGITS
     numerus
    0.55
    chappen
    0.53
     вікі
    0.53
    zionare
    0.53
     CHtml
    0.52
    Datuak
    0.50
    bersicht
    0.50
    ITAN
    0.50
    ggiare
    0.49
    Javadoc
    0.48
    Activations Density 3.348%

    No Known Activations