© 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. 130092
    Prev
    Next
    INDEX
    Explanations

    arcade, code, Party, Parrot

    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
    _
    1.37
    an
    1.32
    os
    1.28
    '
    1.26
    é
    1.23
    ี
    1.23
    ay
    1.21
    y
    1.17
    od
    1.16
    et
    1.14
    POSITIVE LOGITS
    ጨማሪ
    1.30
    ፈላ
    1.19
    መሳሳይ
    1.05
    見
    1.02
    to
    0.99
     Defines
    0.95
    知
    0.95
    表示
    0.95
    forKey
    0.94
    加
    0.93
    Activations Density 0.000%

    No Known Activations