© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162138
    Prev
    Next
    INDEX
    Explanations

    Airfield, University, or field names

    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_2_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
    ﻟ
    1.16
    ج
    1.11
    し
    1.08
    >
    1.05
    ین
    1.02
    ა
    1.02
    The
    1.00
          
    0.95
     probabil
    0.95
    -
    0.95
    POSITIVE LOGITS
    s
    1.55
     for
    1.46
     are
    1.45
    ",
    1.30
    ス
    1.29
    ре
    1.27
    ла
    1.25
    ra
    1.17
    وت
    1.17
    et
    1.16
    Activations Density 0.000%

    No Known Activations