© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75719
    Prev
    Next
    INDEX
    Explanations

    else statement

    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_31_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
    ندو
    0.37
     sugest
    0.36
     complejidad
    0.36
    ুইস
    0.35
    涀
    0.35
     teplot
    0.35
    LaunchScheme
    0.35
     DENUMIRE
    0.34
     modelu
    0.34
    哮
    0.34
    POSITIVE LOGITS
     Plat
    0.36
     Gaz
    0.34
     Sol
    0.32
    ရေး
    0.32
     Биз
    0.32
    However
    0.32
     dictates
    0.32
     plat
    0.32
     favour
    0.31
     অবশ্য
    0.31
    Activations Density 0.002%

    No Known Activations