© 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. 216708
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    बीएसई
    0.46
    Ｗ
    0.42
    ศูนย์
    0.41
    য়নে
    0.41
    𒀊
    0.40
    سو
    0.40
    لیسی
    0.39
     Sue
    0.38
    아가
    0.38
     চালায়
    0.38
    POSITIVE LOGITS
    James
    0.77
     James
    0.74
    james
    0.74
     james
    0.71
    JAMES
    0.61
     JAMES
    0.58
    詹
    0.53
    George
    0.46
     GEORGE
    0.42
     George
    0.40
    Activations Density 0.001%

    No Known Activations