© 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. 61815
    Prev
    Next
    INDEX
    Explanations

    Gauss

    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
    ли
    1.70
    ри
    1.48
    ма
    1.40
    ер
    1.39
    ਾ
    1.27
     ойношот
    1.23
    й
    1.22
    कडून
    1.21
    д
    1.21
    ے
    1.19
    POSITIVE LOGITS
    n
    2.11
    r
    1.77
    time
    1.64
    P
    1.60
    o
    1.55
    td
    1.48
    G
    1.48
    ts
    1.44
    B
    1.40
    x
    1.39
    Activations Density 0.000%

    No Known Activations