© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196320
    Prev
    Next
    INDEX
    Explanations

    strong arm or lift tactics

    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_4_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
     be
    1.11
    ス
    0.96
     an
    0.87
    Y
    0.83
    S
    0.81
    ה
    0.81
     it
    0.79
    V
    0.78
    ส
    0.78
    ్‌
    0.77
    POSITIVE LOGITS
    attiv
    0.61
     cuánt
    0.61
    andha
    0.60
     Матери
    0.59
    ᱕
    0.59
    ämä
    0.58
     익
    0.58
     দামে
    0.58
     시절
    0.58
    량
    0.57
    Activations Density 0.000%

    No Known Activations