© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53799
    Prev
    Next
    INDEX
    Explanations

    unethical concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    []}
    0.39
    utation
    0.37
    በባ
    0.37
    …).
    0.36
    function
    0.35
    CART
    0.35
    ండి
    0.34
    -])
    0.34
    èlement
    0.34
    лизм
    0.34
    POSITIVE LOGITS
    棪
    0.42
     αν
    0.39
     Construction
    0.39
     건설
    0.39
     diat
    0.38
     smears
    0.37
     feedings
    0.37
     CONSTRUCTION
    0.37
    สึก
    0.37
     tendre
    0.36
    Activations Density 0.021%

    No Known Activations