© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214999
    Prev
    Next
    INDEX
    Explanations

    refuge, refusal, refining, refractory

    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_5_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
    تی
    1.50
     of
    1.48
    ین
    1.42
    다
    1.21
    ні
    1.20
    یز
    1.17
    人の
    1.11
    よう
    1.09
    지
    1.09
    ます
    1.08
    POSITIVE LOGITS
    et
    1.02
    ib
    0.97
     ans
    0.93
    five
    0.88
    ли
    0.88
     omt
    0.86
    are
    0.86
    flor
    0.85
    iii
    0.84
    _
    0.84
    Activations Density 0.002%

    No Known Activations