© 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. 39400
    Prev
    Next
    INDEX
    Explanations

    reminds me of

    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
    7
    0.63
    $
    0.63
     Comunicación
    0.62
     comunicación
    0.62
     Лю
    0.61
    $%
    0.61
    1
    0.58
    Know
    0.57
    varlak
    0.57
    Nft
    0.57
    POSITIVE LOGITS
    ání
    0.55
    ERS
    0.55
    ielle
    0.54
    ália
    0.51
    ractors
    0.50
    ers
    0.50
    導致
    0.49
    allows
    0.49
    
    0.48
    творення
    0.48
    Activations Density 0.039%

    No Known Activations