© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36696
    Prev
    Next
    INDEX
    Explanations

    is/are

    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
     trails
    0.37
     చేయ
    0.37
     মুক্তিযোদ্ধারা
    0.35
    Опера
    0.35
     shepherd
    0.35
     ils
    0.34
     reconnaissance
    0.34
    С
    0.33
     opposit
    0.33
    缰
    0.33
    POSITIVE LOGITS
    筤
    0.36
     anything
    0.34
     ਕਿ
    0.34
    `
    0.33
     bustle
    0.33
    avano
    0.33
    junk
    0.32
    論
    0.32
     mungkin
    0.31
     वेस्ट
    0.31
    Activations Density 0.001%

    No Known Activations