© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201238
    Prev
    Next
    INDEX
    Explanations

    cranium

    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
    Negative Logits
    null
    0.45
     null
    0.45
    🕸
    0.44
    ुल्लाह
    0.44
    ulla
    0.41
    Null
    0.40
    ুখ
    0.39
    ullah
    0.38
    ULL
    0.38
    NULL
    0.38
    POSITIVE LOGITS
     bones
    0.45
     Attribute
    0.42
    瓊
    0.42
     Bone
    0.42
     Baj
    0.42
    骨
    0.42
     spine
    0.41
    جرة
    0.40
    বাত
    0.40
    چر
    0.40
    Activations Density 0.000%

    No Known Activations