© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227177
    Prev
    Next
    INDEX
    Explanations

    posts by

    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_6_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
     tunnelling
    0.77
    ิ
    0.76
    し
    0.72
    MktCap
    0.71
     }$
    0.71
    ע
    0.70
    用於
    0.69
    ्रेडिट
    0.69
     répondre
    0.68
    Retry
    0.67
    POSITIVE LOGITS
     by
    1.13
    is
    1.05
    s
    1.05
    at
    1.01
    de
    0.97
    ção
    0.96
    ova
    0.89
    op
    0.89
    3
    0.88
    se
    0.85
    Activations Density 0.003%

    No Known Activations