© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214783
    Prev
    Next
    INDEX
    Explanations

    va and van followed by words

    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_5_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
    は
    1.36
    是
    1.30
    ۔
    1.30
    ס
    1.30
    '
    1.29
    로
    1.25
    ده
    1.23
    در
    1.18
    h
    1.16
    는
    1.16
    POSITIVE LOGITS
    ER
    1.27
     for
    1.24
    ı
    1.10
    ler
    1.09
    ী
    1.07
     at
    1.02
    fø
    1.02
    ă
    0.99
    ü
    0.98
     apoio
    0.95
    Activations Density 0.000%

    No Known Activations