© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258979
    Prev
    Next
    INDEX
    Explanations

    exploitative and harmful

    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_22_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
    ricos
    0.40
    allerg
    0.39
    casino
    0.39
    ijl
    0.38
     எனப்படும்
    0.38
    flags
    0.38
    ihad
    0.38
    $('#
    0.37
     ضر
    0.36
    nom
    0.36
    POSITIVE LOGITS
     us
    0.37
     ce
    0.37
     indicated
    0.35
     Dris
    0.35
     Covers
    0.35
     agnostic
    0.34
     Loves
    0.34
    ྤ
    0.34
     Bis
    0.33
     technically
    0.33
    Activations Density 0.023%

    No Known Activations