© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74958
    Prev
    Next
    INDEX
    Explanations

    build, start, find, go, get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    barrels
    0.33
    mouseDown
    0.32
    亟
    0.32
    Coming
    0.32
    Mét
    0.32
    coming
    0.32
     madd
    0.31
     концентра
    0.31
     sentimento
    0.31
     sentimiento
    0.30
    POSITIVE LOGITS
     szabály
    0.34
     aturan
    0.33
     rule
    0.32
     ask
    0.32
     mention
    0.32
    綗
    0.32
     revoke
    0.31
    atay
    0.31
    ;|
    0.31
     serta
    0.31
    Activations Density 0.003%

    No Known Activations