© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198802
    Prev
    Next
    INDEX
    Explanations

    **protection**

    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_15_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
    res
    0.39
    ンドン
    0.38
     закона
    0.37
     страхо
    0.36
    ݢ
    0.36
    ajemy
    0.36
    idamente
    0.36
    蒖
    0.36
    ยายาม
    0.35
    ayev
    0.35
    POSITIVE LOGITS
     ride
    0.34
    AL
    0.32
     stain
    0.31
    ̀i
    0.31
    土
    0.31
     plant
    0.30
     ornamentation
    0.30
    soort
    0.30
     ring
    0.30
     Ring
    0.29
    Activations Density 0.008%

    No Known Activations