© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210066
    Prev
    Next
    INDEX
    Explanations

    solving things at once

    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_20_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
     disintegr
    0.44
    ProxyAgent
    0.44
     disintegrated
    0.44
     {});
    0.43
    ulfite
    0.40
     frost
    0.40
     bromide
    0.40
    ச்சே
    0.39
    Gap
    0.39
     magnetically
    0.39
    POSITIVE LOGITS
     Standards
    0.43
    ieties
    0.42
     CNG
    0.42
    **************
    0.41
    renzia
    0.40
     Moms
    0.40
    CNC
    0.39
     ನೋಡ
    0.39
    iamo
    0.39
     විශ්
    0.39
    Activations Density 0.000%

    No Known Activations