© 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. 208722
    Prev
    Next
    INDEX
    Explanations

    good

    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
    __
    1.28
    __'
    0.74
    __:
    0.71
    ___
    0.70
    __.
    0.63
    __[
    0.63
    __|
    0.62
    __/
    0.60
    ____
    0.59
    __))
    0.59
    POSITIVE LOGITS
    的神
    0.39
     good
    0.39
    বাহী
    0.38
    volle
    0.38
    Nice
    0.37
    good
    0.37
    0.36
    <unused7>
    0.36
    adequate
    0.36
     guter
    0.36
    Activations Density 0.002%

    No Known Activations