© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150762
    Prev
    Next
    INDEX
    Explanations

    uncensored, censored, dubbed

    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_18_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
    rs
    0.34
     end
    0.33
    0.32
     el
    0.30
     nd
    0.29
     method
    0.28
     ,
    0.28
    _
    0.28
     seldom
    0.27
    *
    0.27
    POSITIVE LOGITS
     culturali
    0.37
     culturale
    0.33
     culturales
    0.33
     культур
    0.32
     polarization
    0.31
    嘖
    0.31
     térmica
    0.31
     pétales
    0.30
     corpore
    0.30
    verständlich
    0.30
    Activations Density 0.002%

    No Known Activations