© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89843
    Prev
    Next
    INDEX
    Explanations

    charcoal stick

    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_3_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
    ו
    0.81
    س
    0.77
    น
    0.76
    I
    0.74
    S
    0.70
    ش
    0.68
    我
    0.67
    T
    0.63
    );}
    0.61
    你
    0.61
    POSITIVE LOGITS
    c
    0.80
    r
    0.78
    ä
    0.76
    ac
    0.73
    w
    0.70
    d
    0.69
    il
    0.66
    руем
    0.66
    he
    0.64
    cooling
    0.63
    Activations Density 0.001%

    No Known Activations