© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40058
    Prev
    Next
    INDEX
    Explanations

    input reading `gets` or `ranges`

    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_11_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
    E
    0.23
    W
    0.22
    H
    0.21
    P
    0.19
    پ
    0.19
    _
    0.19
    ματος
    0.19
    ```
    0.19
    4
    0.19
    O
    0.18
    POSITIVE LOGITS
     Nintendo
    0.17
     Xerox
    0.16
    nto
    0.16
     Xbox
    0.16
     ре
    0.16
    )
    0.16
     Class
    0.16
     Mur
    0.16
     Re
    0.15
     Northern
    0.15
    Activations Density 0.003%

    No Known Activations