© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195266
    Prev
    Next
    INDEX
    Explanations

    server, personas, modes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
    ెక్టర్
    0.54
    ução
    0.52
     واح
    0.48
     《
    0.45
    plotly
    0.45
    textvariable
    0.44
     confiança
    0.42
    "%
    0.42
    :(
    0.41
     paralys
    0.41
    POSITIVE LOGITS
    दो
    0.49
    शासन
    0.49
     bount
    0.49
     noticias
    0.48
     messes
    0.48
     notizie
    0.48
     notícias
    0.48
     revamp
    0.47
     indoct
    0.47
     contin
    0.46
    Activations Density 0.000%

    No Known Activations