© 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. 253257
    Prev
    Next
    INDEX
    Explanations

    and

    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
     والع
    0.39
    بدا
    0.38
    ंसा
    0.37
    ہرست
    0.37
    οντας
    0.36
    读书
    0.35
    ۽
    0.34
    および
    0.34
    }--
    0.34
    }->
    0.34
    POSITIVE LOGITS
     also
    0.69
    also
    0.68
     are
    0.64
     present
    0.64
     ovat
    0.58
     také
    0.57
     therefore
    0.57
     thus
    0.56
     también
    0.54
     sarebbero
    0.54
    Activations Density 0.003%

    No Known Activations