© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209254
    Prev
    Next
    INDEX
    Explanations

    axis of rotation

    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_10_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
    eta
    0.82
    il
    0.80
    ing
    0.79
    ap
    0.78
    ado
    0.74
    iert
    0.71
    c
    0.71
    n
    0.70
    ta
    0.70
    ov
    0.69
    POSITIVE LOGITS
    д
    0.75
    قة
    0.66
    з
    0.65
    지
    0.64
    même
    0.64
     as
    0.63
    ずつ
    0.63
    สี
    0.63
    返す
    0.63
    ຂອງ
    0.62
    Activations Density 0.002%

    No Known Activations