© 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. 90312
    Prev
    Next
    INDEX
    Explanations

    which were

    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
    ка
    0.86
    ном
    0.83
    ي
    0.82
    া
    0.80
    պես
    0.78
    𝚣
    0.76
    ру
    0.75
    د
    0.75
    ન
    0.73
    𝚓
    0.72
    POSITIVE LOGITS
     (
    1.03
     I
    0.90
    S
    0.71
    H
    0.66
     a
    0.66
     h
    0.64
    I
    0.62
     c
    0.61
     U
    0.61
     system
    0.60
    Activations Density 0.000%

    No Known Activations