© 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. 3871
    Prev
    Next
    INDEX
    Explanations

    language typical of legal briefs.

    oai_token-act-pair · gemini-2.0-flash

    court cases

    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
     Normdatei
    -0.63
    UrlResolution
    -0.63
    AsUp
    -0.57
    InputBorder
    -0.54
     MonoBehaviour
    -0.54
    ServletException
    -0.52
     BorderRadius
    -0.52
    帖最后由
    -0.52
    elemField
    -0.50
     Ballard
    -0.50
    POSITIVE LOGITS
    forChild
    0.56
    SequentialGroup
    0.53
    PTI
    0.51
    adé
    0.48
    DebuggerStep
    0.48
    ulents
    0.47
    archiviato
    0.47
     virgins
    0.47
    دانشنامهٔ
    0.46
    تف
    0.46
    Activations Density 6.877%

    No Known Activations