© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105070
    Prev
    Next
    INDEX
    Explanations

    sniffing

    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_1_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
    in
    1.23
    er
    1.22
    um
    1.21
    ians
    1.21
    1.18
    s
    1.18
    ant
    1.17
    nd
    1.15
    o
    1.15
    es
    1.13
    POSITIVE LOGITS
     مكان
    1.00
     convers
    0.98
    எ
    0.97
     Современ
    0.97
     Часто
    0.96
    getBy
    0.96
     Dispon
    0.96
    and
    0.95
     czemu
    0.92
     déta
    0.91
    Activations Density 0.000%

    No Known Activations