© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41906
    Prev
    Next
    INDEX
    Explanations

    draining pasta

    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_22_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
    rency
    0.44
    ineuses
    0.44
     архівної
    0.43
    ॥
    0.40
    맇
    0.40
    سبة
    0.40
    собенно
    0.39
    fourths
    0.39
     homebuyers
    0.39
    क्रेट
    0.38
    POSITIVE LOGITS
    站
    0.36
    ことがあります
    0.35
     permanent
    0.34
    opi
    0.34
     kara
    0.34
     species
    0.34
     relations
    0.34
     உள்ளனர்
    0.34
     প্রজাতির
    0.33
     subst
    0.33
    Activations Density 0.000%

    No Known Activations