© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151231
    Prev
    Next
    INDEX
    Explanations

    the

    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_60_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
     המו
    0.40
    не
    0.40
    네
    0.40
    ن
    0.39
    𝘯
    0.39
    น
    0.38
    n
    0.38
    ně
    0.36
    но
    0.35
     french
    0.35
    POSITIVE LOGITS
     Nottingham
    0.46
     Orioles
    0.45
     DataTypes
    0.44
     Napole
    0.44
     Franken
    0.43
     Fernandes
    0.42
     Bloomberg
    0.42
     Panthers
    0.41
     Villages
    0.41
     Bamberg
    0.40
    Activations Density 0.000%

    No Known Activations