© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79389
    Prev
    Next
    INDEX
    Explanations

    He said his

    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_29_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
     ।
    0.36
     {}".
    0.34
     SED
    0.32
     стране
    0.32
     [],
    0.30
     [\
    0.30
     fromi
    0.30
     स्वा
    0.29
     %\
    0.29
     HOUR
    0.29
    POSITIVE LOGITS
     vitamine
    0.34
     آنها
    0.34
    alin
    0.34
     envisage
    0.33
    presumably
    0.33
    agonal
    0.32
    badan
    0.32
     不是
    0.32
    Რ
    0.31
    لو
    0.31
    Activations Density 0.002%

    No Known Activations