© 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. 107199
    Prev
    Next
    INDEX
    Explanations

    Tornatevene

    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
     can
    1.07
    the
    1.03
    ase
    0.99
    ol
    0.99
    el
    0.93
    é
    0.93
     =
    0.88
    ian
    0.88
     be
    0.86
     för
    0.85
    POSITIVE LOGITS
    স
    1.42
    س
    1.26
    Т
    1.21
    ப
    1.15
    ות
    1.13
    ים
    1.07
    두
    1.07
    ה
    1.06
    টি
    1.05
    К
    1.03
    Activations Density 0.002%

    No Known Activations