© 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. 89639
    Prev
    Next
    INDEX
    Explanations

    onCreate

    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
    та
    0.85
    м
    0.83
    ب
    0.82
    ية
    0.80
    л
    0.80
    на
    0.80
    其
    0.78
    ات
    0.77
    يريا
    0.76
    те
    0.76
    POSITIVE LOGITS
     of
    0.95
     at
    0.63
     as
    0.61
     ऑफ
    0.60
    ICK
    0.60
    far
    0.60
    e
    0.59
     OF
    0.58
    dir
    0.57
    ba
    0.57
    Activations Density 0.000%

    No Known Activations