© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50265
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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_10_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
    tu
    0.83
     ubic
    0.79
     дума
    0.79
    ва
    0.76
     зап
    0.73
     alcanzar
    0.73
     숫자
    0.72
    t
    0.72
     हमने
    0.71
     で
    0.71
    POSITIVE LOGITS
    7
    1.02
    8
    0.96
    AK
    0.89
    HR
    0.86
    Printing
    0.86
    5
    0.86
    PL
    0.83
    OK
    0.82
    2
    0.82
    ET
    0.81
    Activations Density 0.046%

    No Known Activations