© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232612
    Prev
    Next
    INDEX
    Explanations

    curly hair

    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_46_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
     Coll
    0.42
     جان
    0.40
    igroup
    0.40
     Threshold
    0.40
     SSP
    0.40
     Asp
    0.39
     Skin
    0.38
    빙
    0.38
    گز
    0.37
    ंगिक
    0.37
    POSITIVE LOGITS
     curly
    0.39
    Curly
    0.39
     curl
    0.38
     मनोर
    0.38
    提出
    0.38
     declares
    0.37
    udahan
    0.37
     heatmap
    0.36
    alchemy
    0.36
     signaler
    0.36
    Activations Density 0.003%

    No Known Activations