© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232512
    Prev
    Next
    INDEX
    Explanations

    ,

    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_32_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
     replacing
    0.46
    砓
    0.46
     replaced
    0.44
     capitalized
    0.42
     replaces
    0.41
     currently
    0.40
     nitros
    0.39
     capitale
    0.39
     eyeliner
    0.38
    Rosen
    0.38
    POSITIVE LOGITS
    搁
    0.38
    ую
    0.38
     externos
    0.38
    まったく
    0.37
     বহি
    0.37
    outines
    0.36
    མ་
    0.35
     Cond
    0.34
    외부
    0.34
    ndale
    0.34
    Activations Density 0.004%

    No Known Activations