© 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. 201961
    Prev
    Next
    INDEX
    Explanations

    lies a

    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
    i
    1.23
    ي
    1.19
    و
    1.16
    ו
    1.13
    .
    0.96
    א
    0.94
    ে
    0.93
    י
    0.92
    ون
    0.91
     hadrons
    0.89
    POSITIVE LOGITS
    az
    1.01
     was
    0.95
     as
    0.89
    encial
    0.87
     to
    0.86
    ire
    0.85
     É
    0.82
     Бе
    0.82
    ay
    0.80
    ↵
    0.80
    Activations Density 0.000%

    No Known Activations