© 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. 3782
    Prev
    Next
    INDEX
    Explanations

    words related to plumbing or inventions

    oai_token-act-pair · gemini-2.0-flash

    plumbing

    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
    ########.
    -0.63
    fjspx
    -0.59
     بيها
    -0.57
    $_['
    -0.57
     jPanel
    -0.56
    BoxShadow
    -0.56
     ujednoznacz
    -0.55
    RenderAtEndOf
    -0.53
    IndentedString
    -0.53
    UnsafeEnabled
    -0.52
    POSITIVE LOGITS
    museo
    0.47
    Ufficio
    0.47
     bays
    0.47
     brioche
    0.46
     brig
    0.46
     Doch
    0.46
     đính
    0.45
    Premios
    0.45
    XtraEditors
    0.44
    rinol
    0.44
    Activations Density 6.830%

    No Known Activations