© 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. 252877
    Prev
    Next
    INDEX
    Explanations

    admit

    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
     Promise
    0.43
     ак
    0.40
    promise
    0.39
     promise
    0.39
    Promise
    0.38
     ak
    0.38
    ак
    0.38
    ㄴ
    0.38
     PROM
    0.37
    好吧
    0.37
    POSITIVE LOGITS
     admit
    0.45
    ൂടെ
    0.43
     confess
    0.42
     admitting
    0.40
     confesses
    0.39
     mean
    0.38
    룹
    0.38
     tops
    0.38
     Tops
    0.37
    mä
    0.36
    Activations Density 0.003%

    No Known Activations