© 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. 4179
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers, warranty information, or phrases related to finding a partner

    oai_token-act-pair · gemini-2.0-flash

    Legal and online text

    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
     the
    -0.78
    ed
    -0.69
     to
    -0.69
     for
    -0.67
     OF
    -0.66
     that
    -0.66
     on
    -0.64
     in
    -0.63
    the
    -0.63
     from
    -0.61
    POSITIVE LOGITS
    overhead
    0.45
    jface
    0.44
    fontawesome
    0.43
    uterine
    0.43
     GRAY
    0.41
    DUC
    0.41
    PSON
    0.41
     ROGERS
    0.41
    CURY
    0.41
     Commencez
    0.41
    Activations Density 8.972%

    No Known Activations