© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8494
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    cl
    0.06
     Q
    0.06
    gies
    0.06
    曺
    0.06
     নিত্য
    0.06
     biz
    0.06
     offen
    0.06
     belles
    0.06
     gy
    0.06
     ry
    0.06
    POSITIVE LOGITS
     gonflement
    0.06
     ставак
    0.06
     Zapata
    0.06
    槓
    0.06
    活跃
    0.06
    ेशंस
    0.06
     isKindOfClass
    0.06
     dissociation
    0.05
    ﮢ
    0.05
    পত
    0.05
    Activations Density 0.613%

    No Known Activations