© 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. 220387
    Prev
    Next
    INDEX
    Explanations

    c code includes

    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
    綘
    0.32
     بیٹنگ
    0.29
    LastName
    0.28
     riqueza
    0.28
    ICIENCY
    0.28
    တိုင်း
    0.27
    тивная
    0.27
    Trac
    0.27
    ESSITY
    0.26
     счастли
    0.25
    POSITIVE LOGITS
     বস্তু
    0.31
     ooit
    0.29
     footsteps
    0.28
    }=(
    0.28
    }^{(\
    0.28
    onbury
    0.27
     disamb
    0.27
     पप्पू
    0.27
     COOK
    0.26
     transform
    0.26
    Activations Density 0.000%

    No Known Activations