© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196546
    Prev
    Next
    INDEX
    Explanations

    Spanish words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    TOR
    0.43
    ([])
    0.40
    Torch
    0.40
    ោង
    0.40
    Exp
    0.38
     torch
    0.38
     exped
    0.38
     KP
    0.37
    (["
    0.37
    ючи
    0.37
    POSITIVE LOGITS
     vos
    0.47
    Vos
    0.42
     concret
    0.42
     Bole
    0.42
    concret
    0.41
    巴巴
    0.40
     Vos
    0.39
     carbono
    0.39
     encar
    0.39
     цикл
    0.39
    Activations Density 0.002%

    No Known Activations