© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4135
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, locations, and organizations, especially as they relate to Africa

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    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
    endpush
    -0.69
     BoxFit
    -0.66
     Мексичка
    -0.57
    sidemargin
    -0.56
    windowFixed
    -0.56
     useStyles
    -0.55
    ftagPool
    -0.53
    usky
    -0.51
     endblock
    -0.51
     resourceCulture
    -0.50
    POSITIVE LOGITS
    reiten
    0.53
    $=
    0.49
     clínico
    0.49
     solidarité
    0.48
     chaleur
    0.48
     tarko
    0.48
     hausse
    0.47
    $
    0.45
    \$
    0.45
     gravedad
    0.44
    Activations Density 6.383%

    No Known Activations