© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159534
    Prev
    Next
    INDEX
    Explanations

    paraphrase

    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_2_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
    s
    2.25
    in
    2.14
    ς
    1.72
    ی
    1.57
    en
    1.53
    ség
    1.29
    ের
    1.24
    т
    1.23
    y
    1.20
    sels
    1.20
    POSITIVE LOGITS
     is
    1.16
     hebat
    1.09
    ud
    1.08
    大
    1.07
     or
    1.03
    ৩
    1.03
    ุ
    1.01
    ので
    0.97
    om
    0.96
    6
    0.95
    Activations Density 0.001%

    No Known Activations