© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26302
    Prev
    Next
    INDEX
    Explanations

    the initiative

    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_10_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
    N
    0.40
    ai
    0.39
    вання
    0.39
    ни
    0.39
    y
    0.39
    ab
    0.39
    ступ
    0.39
    ги
    0.39
    بي
    0.38
    ag
    0.38
    POSITIVE LOGITS
     collinear
    0.39
    ு
    0.38
     forgo
    0.37
     outstretched
    0.35
    ikt
    0.33
     cheesy
    0.32
     galloping
    0.32
     შემთხვევაში
    0.32
     formula
    0.31
     saliva
    0.31
    Activations Density 0.009%

    No Known Activations