© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157396
    Prev
    Next
    INDEX
    Explanations

    subprocess calls

    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
    ED
    1.66
    AD
    1.65
    માં
    1.47
    ক
    1.46
    AN
    1.45
    AV
    1.44
    IB
    1.44
    ए
    1.40
    AL
    1.39
    OT
    1.39
    POSITIVE LOGITS
    ли
    1.86
    لي
    1.52
    li
    1.45
    dır
    1.27
    ۹
    1.23
    ৮
    1.20
    دن
    1.19
    ти
    1.16
    la
    1.16
     fluctu
    1.16
    Activations Density 0.001%

    No Known Activations