© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50931
    Prev
    Next
    INDEX
    Explanations

    numbered districts

    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_55_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
    ght
    0.57
    ｬ
    0.55
    ゅう
    0.52
    ｭ
    0.52
    ョン
    0.51
    ｮ
    0.49
    onnés
    0.47
    ère
    0.46
    ョ
    0.44
    руется
    0.43
    POSITIVE LOGITS
     Biggest
    0.39
    ഏ
    0.38
    ведении
    0.38
    ái
    0.37
    ᱟ
    0.37
    eyiz
    0.36
    bewegung
    0.35
     UAV
    0.35
     Srbije
    0.35
     Ministerial
    0.35
    Activations Density 0.021%

    No Known Activations