© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236338
    Prev
    Next
    INDEX
    Explanations

    loyalty

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    喱
    0.45
     toe
    0.39
     கூட்டணிய
    0.39
    preset
    0.38
    жают
    0.38
    hid
    0.38
    喂
    0.38
    сон
    0.37
     взял
    0.37
    toe
    0.36
    POSITIVE LOGITS
     sas
    0.40
     annotation
    0.39
     review
    0.38
     Messaging
    0.38
     funkcji
    0.38
    */
    0.37
    </ul>
    0.37
    adiene
    0.37
     ses
    0.37
     Approach
    0.36
    Activations Density 0.002%

    No Known Activations