© 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. 35912
    Prev
    Next
    INDEX
    Explanations

    step-by-step explanation

    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
    ח
    0.79
    ש
    0.72
    ل
    0.68
     sunrise
    0.61
     disturbs
    0.61
     skyline
    0.60
    க்கு
    0.60
    б
    0.60
     premio
    0.59
    тным
    0.57
    POSITIVE LOGITS
    ها
    0.68
    та
    0.64
     and
    0.63
    and
    0.59
     któ
    0.59
    am
    0.58
    ing
    0.58
    es
    0.56
    on
    0.56
    are
    0.55
    Activations Density 0.001%

    No Known Activations