© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91380
    Prev
    Next
    INDEX
    Explanations

    figure skating events

    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_11_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
    iet
    0.55
    iec
    0.49
     इंस्पेक्टर
    0.49
     Repairs
    0.47
    Ch
    0.47
     l
    0.46
     gör
    0.46
     Ears
    0.46
    q
    0.46
     dinero
    0.44
    POSITIVE LOGITS
     présentes
    0.48
    ansson
    0.43
     ceded
    0.43
    PARATOR
    0.42
    FirstFit
    0.42
     penghargaan
    0.41
    సో
    0.41
    開發
    0.40
    郁
    0.40
    mluv
    0.40
    Activations Density 0.009%

    No Known Activations