© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227133
    Prev
    Next
    INDEX
    Explanations

    let me know

    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_6_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
    in
    1.31
    ین
    1.17
     is
    1.12
    ہ
    1.11
    ان
    1.07
    ות
    1.03
     in
    1.01
    其他
    1.01
     other
    0.98
     altre
    0.97
    POSITIVE LOGITS
    B
    1.05
    ulation
    1.05
    C
    1.04
    on
    1.02
    MSA
    0.91
    ST
    0.88
    SE
    0.88
    MA
    0.88
    Glo
    0.86
    이다
    0.84
    Activations Density 0.005%

    No Known Activations