© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7308
    Prev
    Next
    INDEX
    Explanations

    endanger children

    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_39_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
     En
    0.45
     エン
    0.40
     enclave
    0.39
     en
    0.39
    rolled
    0.38
    ঢ
    0.38
     enclosures
    0.37
     Chile
    0.37
    ೇಶ
    0.37
    zyme
    0.36
    POSITIVE LOGITS
    ുകളിൽ
    0.38
    burse
    0.38
    badbreak
    0.38
    を受けた
    0.36
    口座
    0.36
    মরা
    0.35
    裘
    0.35
     প্রচারিত
    0.34
    createStatement
    0.34
     ಸ್ಥಾನ
    0.34
    Activations Density 0.027%

    No Known Activations