© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34230
    Prev
    Next
    INDEX
    Explanations

    vertices, vertical

    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_3_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
    ский
    0.95
    る
    0.80
    した
    0.76
    de
    0.75
    িত
    0.75
    ية
    0.74
    あ
    0.72
     Бүген
    0.71
     Спорттук
    0.70
    ס
    0.70
    POSITIVE LOGITS
    >
    0.92
    at
    0.84
    "
    0.83
    *
    0.80
    u
    0.79
    Vert
    0.74
     вертика
    0.69
    0.66
    Frank
    0.65
              
    0.64
    Activations Density 0.016%

    No Known Activations