© 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. 40099
    Prev
    Next
    INDEX
    Explanations

    first time

    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
     Databases
    0.62
    槊
    0.61
     سوريا
    0.60
     Disbursements
    0.59
     Seç
    0.59
    )。
    0.58
    Referências
    0.57
     стала
    0.56
     EXIST
    0.56
     Poincaré
    0.56
    POSITIVE LOGITS
    et
    0.66
    كة
    0.57
    atud
    0.56
    ί
    0.55
    red
    0.54
    uiten
    0.53
     called
    0.53
    व
    0.53
    ings
    0.52
    ine
    0.52
    Activations Density 0.000%

    No Known Activations