© 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. 219598
    Prev
    Next
    INDEX
    Explanations

    bounce off boundaries

    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
    Anderson
    0.43
    唂
    0.42
     coexistence
    0.38
    ಚಿ
    0.38
    yect
    0.36
    
    0.36
     الإلكتر
    0.36
    ச்செய
    0.36
    ⎢
    0.36
    ํา
    0.35
    POSITIVE LOGITS
     Bor
    0.37
     moreover
    0.36
     Lok
    0.36
    ormais
    0.35
     durability
    0.35
     Außerdem
    0.35
     floor
    0.34
     Phong
    0.34
     დღ
    0.34
     ట్ర
    0.34
    Activations Density 0.001%

    No Known Activations