© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41753
    Prev
    Next
    INDEX
    Explanations

    risk-free

    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
    3
    0.95
     as
    0.77
    ۳
    0.75
    (
    0.75
    s
    0.73
    স
    0.71
    ३
    0.68
     integra
    0.68
    ក
    0.67
     اینکه
    0.65
    POSITIVE LOGITS
    IN
    0.63
    igree
    0.62
    大致
    0.58
    uch
    0.58
    lama
    0.56
    لم
    0.55
     vermelho
    0.55
    iD
    0.54
    سبة
    0.53
    ン
    0.53
    Activations Density 0.012%

    No Known Activations