© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45822
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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_22_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
    </tbody>
    0.23
     écran
    0.22
    rays
    0.22
     spontaneity
    0.21
    口的
    0.21
    ঞ্চলের
    0.21
    chemicals
    0.21
    ocaust
    0.21
    geoip
    0.21
    ischen
    0.20
    POSITIVE LOGITS
     tao
    0.24
    Begin
    0.23
    丏
    0.23
    ्यादा
    0.23
    Tao
    0.22
    瀹
    0.22
     कुर्सी
    0.21
    ंक्शन
    0.21
    Imperial
    0.21
    Visiting
    0.21
    Activations Density 0.013%

    No Known Activations