© 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. 130146
    Prev
    Next
    INDEX
    Explanations

    places and neighborhoods

    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
    盖
    0.40
     поз
    0.39
     Stroke
    0.38
    ografia
    0.38
     гало
    0.38
     DCHECK
    0.37
    রাপ
    0.37
     coppia
    0.37
     thỏa
    0.37
     bgcolor
    0.36
    POSITIVE LOGITS
     N
    0.44
    找到
    0.40
    Southeast
    0.40
    ND
    0.40
     FERN
    0.39
     Н
    0.38
     الن
    0.38
     бала
    0.38
     SE
    0.38
    ईआरटी
    0.38
    Activations Density 0.001%

    No Known Activations