© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20320
    Prev
    Next
    INDEX
    Explanations

    extreme

    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
     extreme
    2.23
    Extreme
    2.14
    極
    2.11
    extreme
    2.09
     Extreme
    2.08
    极
    2.05
     ekstrem
    1.84
     extrem
    1.77
    extrem
    1.73
     cực
    1.66
    POSITIVE LOGITS
    ity
    0.49
    ITY
    0.44
    न्नी
    0.39
     наверное
    0.38
     కాని
    0.38
    itys
    0.38
    ️
    0.37
    itates
    0.36
    пор
    0.36
    مک
    0.36
    Activations Density 0.001%

    No Known Activations