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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14772
    Prev
    Next
    INDEX
    Explanations

    code and legal text snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     still
    -1.10
    still
    -1.02
    Still
    -0.97
     Still
    -0.95
     masih
    -0.92
     fortfarande
    -0.92
     ainda
    -0.84
     todavía
    -0.83
     هنوز
    -0.83
     ancora
    -0.81
    POSITIVE LOGITS
    ScopeManager
    0.64
    ValueStyle
    0.64
     Infórmanos
    0.60
     تضيفلها
    0.59
    RegistryLite
    0.58
     artık
    0.57
    EndTag
    0.55
     endregion
    0.54
    cipit
    0.53
    ftagPool
    0.53
    Activations Density 1.080%

    No Known Activations