© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89392
    Prev
    Next
    INDEX
    Explanations

    annual reports and credit

    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_3_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
    תו
    0.73
    S
    0.68
    ྪ
    0.68
    ่า
    0.65
    ırm
    0.64
     a
    0.63
    ά
    0.63
    ヴェ
    0.63
     unanim
    0.62
    M
    0.62
    POSITIVE LOGITS
    ag
    0.79
    on
    0.72
    人
    0.70
    ن
    0.68
    ed
    0.64
    ing
    0.63
    ра
    0.63
    ोन
    0.63
    ال
    0.62
    ized
    0.61
    Activations Density 0.001%

    No Known Activations