© 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. 35950
    Prev
    Next
    INDEX
    Explanations

    annual general meeting

    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
    is
    1.09
    er
    1.02
    ing
    0.98
    ال
    0.82
    ط
    0.80
    ah
    0.74
    ن
    0.73
    an
    0.72
    el
    0.72
    can
    0.71
    POSITIVE LOGITS
    ی
    0.75
    ের
    0.74
    ओं
    0.71
    س
    0.71
     in
    0.70
    もら
    0.68
    ים
    0.66
     blocked
    0.63
    s
    0.61
    ও
    0.60
    Activations Density 0.001%

    No Known Activations