© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35320
    Prev
    Next
    INDEX
    Explanations

    Athens

    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_50_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
     phyl
    0.39
    ATH
    0.38
     Cumulative
    0.37
     वारा
    0.37
     ανθ
    0.37
     orthonormal
    0.36
     画
    0.36
    {~
    0.36
     ਕਰੋ
    0.35
    وزر
    0.35
    POSITIVE LOGITS
     Att
    1.20
    Att
    1.12
     att
    1.00
    att
    0.84
     Attic
    0.78
     ATT
    0.65
    Attk
    0.60
    ATT
    0.60
     atta
    0.60
     attenuation
    0.59
    Activations Density 0.003%

    No Known Activations