© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63730
    Prev
    Next
    INDEX
    Explanations

    misgendering

    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_46_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
    访
    0.43
    initis
    0.42
    modeling
    0.39
     amateur
    0.38
    проце
    0.37
     modelling
    0.37
    predicted
    0.37
     polys
    0.36
    頭
    0.36
     hinted
    0.36
    POSITIVE LOGITS
     Advers
    0.37
     ހ
    0.37
    বান
    0.37
    SKI
    0.37
    Particle
    0.36
     bremsstrahlung
    0.36
     〢
    0.36
     hate
    0.35
    <unused69>
    0.35
    FULLY
    0.34
    Activations Density 0.003%

    No Known Activations