© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171012
    Prev
    Next
    INDEX
    Explanations

    frequency and repetition

    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_20_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
     Geschä
    0.29
    TextAlign
    0.27
    𝐭
    0.27
    elolaan
    0.27
    ዝ
    0.27
    égation
    0.26
    Son
    0.26
    κό
    0.26
    ucos
    0.26
    INOIS
    0.25
    POSITIVE LOGITS
     භාවිත
    0.32
     tiring
    0.31
     usi
    0.30
     firearms
    0.29
     worrying
    0.28
     gebruik
    0.28
     repetitive
    0.28
     tirelessly
    0.27
    唧
    0.27
     pumping
    0.27
    Activations Density 0.042%

    No Known Activations