© 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. 39010
    Prev
    Next
    INDEX
    Explanations

    Jane SmithLane Lines

    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
    ic
    0.65
    ac
    0.62
    an
    0.59
    ل
    0.57
    ان
    0.56
    atches
    0.56
    V
    0.56
    ۲
    0.55
    گر
    0.55
    A
    0.55
    POSITIVE LOGITS
    ง
    0.75
    си
    0.68
    ле
    0.65
    ти
    0.62
     Fisica
    0.61
     което
    0.60
     التمثيل
    0.59
    。
    0.59
    та
    0.58
     fisica
    0.58
    Activations Density 0.007%

    No Known Activations