© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6868
    Prev
    Next
    INDEX
    Explanations

    overgeneralization, overruns, overspeed

    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_40_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
    涳
    0.43
    Buying
    0.39
     domic
    0.39
     $\{(
    0.39
     purchasing
    0.39
    ّٰ
    0.39
    终
    0.38
     domicile
    0.38
    \}^{
    0.37
    bought
    0.37
    POSITIVE LOGITS
    Weight
    0.44
     Weight
    0.42
    WEIGHT
    0.40
     ზ
    0.39
     बजट
    0.38
    weight
    0.38
     ventre
    0.38
    SEX
    0.35
    Generation
    0.34
    heads
    0.34
    Activations Density 0.042%

    No Known Activations