© 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. 38245
    Prev
    Next
    INDEX
    Explanations

    IDA and AIDA

    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
    <0x0D>
    0.93
     as
    0.84
    وم
    0.78
    </h3>
    0.77
    </h2>
    0.75
    </li>
    0.73
    ।
    0.73
    ‬
    0.72
    יות
    0.71
    。
    0.70
    POSITIVE LOGITS
    u
    0.62
     пыта
    0.62
     ')
    0.60
    kenalkan
    0.58
     getan
    0.57
    T
    0.57
    镛
    0.56
     pouquinho
    0.56
     tastefully
    0.56
    kan
    0.55
    Activations Density 0.001%

    No Known Activations