© 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. 62396
    Prev
    Next
    INDEX
    Explanations

    map lam tem

    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
    ו
    1.13
     in
    1.12
     It
    1.02
    ра
    1.00
     inorder
    0.93
    د
    0.92
    リ
    0.91
    URE
    0.91
    ी
    0.91
     विपक्ष
    0.89
    POSITIVE LOGITS
    V
    1.55
    T
    1.54
    G
    1.54
    F
    1.49
    M
    1.45
    ↵
    1.41
    L
    1.38
    W
    1.36
    K
    1.36
    S
    1.34
    Activations Density 0.003%

    No Known Activations