© 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. 201171
    Prev
    Next
    INDEX
    Explanations

    to be helpful and harmless

    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
    ли
    1.11
    ,
    0.99
    ти
    0.95
     "),
    0.95
    hasta
    0.93
    8
    0.92
     ",
    0.89
    را
    0.86
     Jawa
    0.86
    라인
    0.86
    POSITIVE LOGITS
    b
    1.07
    า
    0.94
    '
    0.93
    a
    0.89
    <0x80>
    0.82
    an
    0.80
    </h3>
    0.77
    )
    0.75
    '/>
    0.73
    '$
    0.73
    Activations Density 0.005%

    No Known Activations