© 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. 86385
    Prev
    Next
    INDEX
    Explanations

    phantom limb, Coolidge, rally, Everglades

    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
    煕
    0.58
    1
    0.55
    一
    0.54
    ```
    0.53
    lcii
    0.53
    \
    0.53
     اب
    0.52
     थोड़ा
    0.52
    淀
    0.52
    隻
    0.51
    POSITIVE LOGITS
    на
    0.68
    io
    0.64
    iar
    0.64
    iu
    0.63
    e
    0.62
    يًا
    0.62
    ியா
    0.60
    يح
    0.59
    iin
    0.58
    im
    0.58
    Activations Density 0.000%

    No Known Activations