© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170592
    Prev
    Next
    INDEX
    Explanations

    bias or partial

    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_56_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
    Js
    0.43
    STI
    0.40
    JSX
    0.38
    동산
    0.37
    avení
    0.37
    ogon
    0.36
    modulo
    0.36
    浔
    0.36
    ALSE
    0.35
     JS
    0.35
    POSITIVE LOGITS
    偏
    1.88
    片
    1.07
     biased
    1.04
     편
    1.02
     partisan
    0.99
     bias
    0.97
    편
    0.95
    片的
    0.93
     partial
    0.90
     biases
    0.85
    Activations Density 0.000%

    No Known Activations