© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53321
    Prev
    Next
    INDEX
    Explanations

    if

    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_55_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
     though
    0.48
    though
    0.44
    
    0.44
    чень
    0.41
     отсутствие
    0.41
     Though
    0.41
     diferenciar
    0.40
     choć
    0.40
    {|\
    0.40
    或
    0.40
    POSITIVE LOGITS
     small
    0.42
     unspecified
    0.39
     far
    0.38
    ጠና
    0.38
     cou
    0.37
    ench
    0.36
     borne
    0.36
     rational
    0.36
     rooted
    0.36
    讪
    0.36
    Activations Density 0.017%

    No Known Activations