© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215156
    Prev
    Next
    INDEX
    Explanations

    ancient Greek history

    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_50_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
     Mon
    0.42
     ড
    0.42
    BlockHash
    0.42
     Tash
    0.41
     Paw
    0.41
     Rie
    0.41
    Distribution
    0.40
    Paw
    0.39
    ລ
    0.39
     maturation
    0.39
    POSITIVE LOGITS
    signin
    0.44
    nextInt
    0.43
     پس
    0.42
    responsibility
    0.42
     ответственности
    0.40
     P
    0.39
     pin
    0.39
    compar
    0.39
    ivu
    0.39
    പ്
    0.39
    Activations Density 0.000%

    No Known Activations