© 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. 205292
    Prev
    Next
    INDEX
    Explanations

    say "__("

    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
     class
    0.52
     ,"
    0.46
    ,",
    0.41
    --"
    0.41
    +'-
    0.41
    class
    0.40
     ,'
    0.39
    [-
    0.38
    ,"\
    0.37
    —“
    0.37
    POSITIVE LOGITS
    VAL
    0.46
     VAL
    0.40
     சாத
    0.39
     स्मारक
    0.39
     Hello
    0.38
     pricey
    0.36
    val
    0.35
     আলোচ
    0.35
     poveć
    0.35
     Val
    0.34
    Activations Density 0.001%

    No Known Activations