© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34864
    Prev
    Next
    INDEX
    Explanations

    point A to point B

    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
    ের
    0.75
    কে
    0.57
    ಮ
    0.56
    อบ
    0.55
    ड
    0.55
    ים
    0.54
    }$-(
    0.53
    IL
    0.51
    iz
    0.51
    Im
    0.51
    POSITIVE LOGITS
     for
    0.95
    er
    0.87
    i
    0.77
    ي
    0.72
    ー
    0.71
    ния
    0.69
    elat
    0.69
    t
    0.68
    э
    0.68
    ு
    0.67
    Activations Density 0.005%

    No Known Activations