© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169085
    Prev
    Next
    INDEX
    Explanations

    claims and calculation

    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
     точки
    0.39
     muß
    0.38
     COMMISSION
    0.36
     "));
    0.36
    --
    0.36
    Points
    0.36
     въ
    0.36
     내
    0.36
    Commission
    0.36
    ﻝ
    0.36
    POSITIVE LOGITS
    ว่าจะ
    0.37
     வேளா
    0.37
    зяржа
    0.36
     אטאטורק
    0.36
    ımızı
    0.36
     पूर्ण
    0.36
     সমূহ
    0.36
     zajedno
    0.36
    ₊
    0.36
     oppressive
    0.35
    Activations Density 0.000%

    No Known Activations