© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24446
    Prev
    Next
    INDEX
    Explanations

    Spr

    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_56_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
    肚子
    0.35
    忻
    0.35
    塌
    0.35
    ្រ
    0.34
    datab
    0.34
    尃
    0.34
    PathOf
    0.33
     fetal
    0.33
    汜
    0.32
    াকিস্ত
    0.32
    POSITIVE LOGITS
     Spr
    3.17
    Spr
    3.17
     spr
    3.03
    spr
    2.92
     SPR
    2.50
    SPR
    2.50
     스프
    2.48
     спри
    2.27
     Sprague
    2.14
     sprink
    2.08
    Activations Density 0.043%

    No Known Activations