© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53440
    Prev
    Next
    INDEX
    Explanations

    They

    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_55_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
     मज
    0.41
    ໋
    0.41
     offense
    0.40
     ছিলাম
    0.38
     melawan
    0.36
     mastered
    0.36
     remedied
    0.36
    importDefault
    0.36
    ْع
    0.35
    து
    0.35
    POSITIVE LOGITS
    其實
    0.46
     Prize
    0.44
     Actually
    0.41
     Profess
    0.40
     actually
    0.40
    turns
    0.39
     Prizes
    0.39
    Sorter
    0.39
    連接
    0.38
     faktisk
    0.38
    Activations Density 0.001%

    No Known Activations