© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79714
    Prev
    Next
    INDEX
    Explanations

    cash

    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_0_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
    на
    1.83
    ۔
    1.48
    ам
    1.46
    ро
    1.34
    ん
    1.32
    ру
    1.27
    다
    1.27
    ون
    1.27
     cristianos
    1.20
    ρα
    1.19
    POSITIVE LOGITS
     that
    1.73
     of
    1.50
    /
    1.44
    ;
    1.36
    ",
    1.32
    inis
    1.30
     with
    1.27
    ett
    1.26
    n
    1.25
    el
    1.23
    Activations Density 0.001%

    No Known Activations