© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9060
    Prev
    Next
    INDEX
    Explanations

    physical restraint, bondage, or confinement

    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_13_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
    MORD
    0.50
    </footer>
    0.48
     paz
    0.46
     teenager
    0.45
     bárm
    0.45
    ㄵ
    0.45
     სას
    0.44
    );">
    0.44
    ɟ
    0.44
     laughable
    0.44
    POSITIVE LOGITS
     comptes
    0.55
    er
    0.54
    accounts
    0.53
    ilinear
    0.52
    ter
    0.52
    c
    0.51
     planner
    0.51
    bot
    0.50
     caroten
    0.50
    ﺭ
    0.50
    Activations Density 0.000%

    No Known Activations