© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30799
    Prev
    Next
    INDEX
    Explanations

    table structure

    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_7_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
    ጠቀም
    0.56
    μάτων
    0.48
    心
    0.48
     nó
    0.47
    過
    0.46
    好
    0.45
    涼
    0.45
    ∑</
    0.45
    πό
    0.45
    ደበ
    0.45
    POSITIVE LOGITS
    o
    0.78
    la
    0.77
    a
    0.68
    lu
    0.66
    on
    0.65
    as
    0.64
    in
    0.64
    ne
    0.61
    er
    0.59
    da
    0.58
    Activations Density 0.002%

    No Known Activations