© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231681
    Prev
    Next
    INDEX
    Explanations

    expletives and profanity

    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_6_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
    ov
    1.27
    ou
    1.13
    ol
    1.13
    리
    1.13
    el
    1.11
    aid
    1.10
    V
    1.10
    ap
    1.07
    em
    1.06
    ep
    1.06
    POSITIVE LOGITS
    𝙠
    0.95
    ের
    0.95
    𝙩
    0.94
    𝙣
    0.90
    ся
    0.89
     underlies
    0.89
     equivoc
    0.89
    𝙜
    0.89
     ensues
    0.89
     onun
    0.88
    Activations Density 0.000%

    No Known Activations