© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2149
    Prev
    Next
    INDEX
    Explanations

    capitalized names of people, places, companies, and organizations

    oai_token-act-pair · gemini-2.0-flash

    names

    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
    脚注の使い方
    -0.70
     vectorielles
    -0.66
     défauts
    -0.64
     excès
    -0.63
    IUrlHelper
    -0.63
     समीक्षक
    -0.63
    RenderAtEndOf
    -0.60
     intptr
    -0.60
    providedIn
    -0.59
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
    stoke
    0.49
     Kaufman
    0.36
     Levinson
    0.35
     dormit
    0.35
    brook
    0.34
    necedor
    0.33
     Varela
    0.33
    Asia
    0.33
     Schultz
    0.33
    dahl
    0.33
    Activations Density 21.431%

    No Known Activations