© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11125
    Prev
    Next
    INDEX
    Explanations

    technical writing about electricity

    oai_token-act-pair · gemini-2.0-flash

    static electricity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    InvalidProtocol
    -0.65
    >%
    -0.57
    //
    -0.55
     Приступљено
    -0.53
    migrationBuilder
    -0.52
    ModelAdmin
    -0.52
    ']))
    -0.52
     MainAxisSize
    -0.52
    '))
    -0.51
     doInBackground
    -0.51
    POSITIVE LOGITS
     static
    1.17
    static
    1.01
     STATIC
    0.94
     Static
    0.94
    Static
    0.86
    STATIC
    0.78
    静
    0.66
     discharging
    0.65
     静
    0.65
     discharges
    0.64
    Activations Density 2.865%

    No Known Activations