© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109052
    Prev
    Next
    INDEX
    Explanations

    pioneers and reckoned

    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_1_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
    .
    1.27
    -
    1.20
    I
    1.09
     في
    1.06
    是
    1.02
    \
    1.01
    *
    0.99
    '
    0.98
    ,
    0.97
    al
    0.95
    POSITIVE LOGITS
    ו
    1.71
    ه‌های
    1.18
    ه‌ای
    1.18
    ه‌ی
    1.13
    த்தில்
    1.12
    وری
    1.12
    واری
    1.09
    که
    1.08
    یس
    1.03
    েও
    1.03
    Activations Density 0.000%

    No Known Activations