© 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. 24204
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     tři
    0.77
     three
    0.77
     trois
    0.73
     trzy
    0.70
     five
    0.68
     seven
    0.67
     ৩
    0.67
     మూడు
    0.66
     तीन
    0.65
     quatre
    0.65
    POSITIVE LOGITS
    Two
    0.55
    Four
    0.50
    One
    0.49
    Ten
    0.46
    „
    0.44
     Two
    0.43
    person
    0.43
    Six
    0.43
    :(
    0.43
    Forty
    0.42
    Activations Density 0.009%

    No Known Activations