© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103095
    Prev
    Next
    INDEX
    Explanations

    SNOWFLAKE FL keywords

    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_1_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
    D
    1.75
    ۔
    1.66
    N
    1.59
    P
    1.56
    T
    1.41
    V
    1.41
    R
    1.37
    G
    1.34
    C
    1.31
    ي
    1.29
    POSITIVE LOGITS
    ين
    1.12
     have
    0.94
     was
    0.91
     de
    0.89
    t
    0.89
    ியின்
    0.89
    ก
    0.89
    ер
    0.88
     höch
    0.85
    ет
    0.84
    Activations Density 0.000%

    No Known Activations