© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 761
    Prev
    Next
    INDEX
    Explanations

    dates, names, titles, and affiliations

    oai_token-act-pair · gemini-2.0-flash

    Dash or parenthesis

    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
     Houſe
    -0.93
     itſelf
    -0.87
     Theſe
    -0.84
     Anſ
    -0.82
     Majefty
    -0.81
     Monfieur
    -0.78
     ་་
    -0.77
     myſelf
    -0.72
     Shakspeare
    -0.71
     houſe
    -0.70
    POSITIVE LOGITS
    يديا
    0.57
    conse
    0.52
    bail
    0.52
    neither
    0.51
    deceased
    0.50
    deb
    0.50
    IZO
    0.50
    FFIX
    0.49
    NIV
    0.49
    SOLE
    0.48
    Activations Density 12.274%

    No Known Activations