© 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. 155235
    Prev
    Next
    INDEX
    Explanations

    Something

    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
    ᖏ
    0.39
    ີນ
    0.38
     家
    0.38
     Wrist
    0.37
     unf
    0.37
    álny
    0.37
     கேள்வி
    0.36
    لمانيا
    0.36
     Taschen
    0.36
     pracovní
    0.36
    POSITIVE LOGITS
    pra
    0.43
     புர
    0.42
    <unused97>
    0.41
    र्ड
    0.38
    Pra
    0.38
    tit
    0.37
    就能
    0.37
    mapi
    0.37
    oph
    0.37
    ደት
    0.37
    Activations Density 0.003%

    No Known Activations