© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131275
    Prev
    Next
    INDEX
    Explanations

    dumping or borne

    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
    ي
    1.72
    t
    1.47
    a
    1.40
    d
    1.37
    y
    1.26
    ę
    1.26
    ł
    1.23
    ми
    1.20
    ak
    1.19
    ت
    1.16
    POSITIVE LOGITS
     have
    1.31
     be
    1.30
     a
    1.19
    場合
    1.12
     e
    1.11
    I
    1.01
     you
    0.97
    れる
    0.96
     are
    0.87
    ט
    0.87
    Activations Density 0.002%

    No Known Activations