© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152458
    Prev
    Next
    INDEX
    Explanations

    hereafter devised, hereafter come

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     creates
    0.38
     oferty
    0.38
    異
    0.36
    क्षम
    0.35
     maintains
    0.35
    ల్లి
    0.34
    гене
    0.33
     Maintains
    0.33
    异
    0.33
    ржа
    0.33
    POSITIVE LOGITS
    suited
    0.41
    inflammation
    0.38
    suit
    0.37
    vection
    0.37
    yyam
    0.36
    ዎቹ
    0.36
    theory
    0.36
    cido
    0.35
    citations
    0.35
     suited
    0.35
    Activations Density 0.000%

    No Known Activations