© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211213
    Prev
    Next
    INDEX
    Explanations

    mood board

    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_5_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
    ма
    1.28
    اين
    1.28
    ш
    1.25
    ну
    1.14
    ב
    1.13
    нда
    1.03
    رك
    1.02
    iellement
    1.02
    ৪
    1.02
    ейчас
    1.00
    POSITIVE LOGITS
     is
    1.33
     (
    1.13
    -
    1.09
    1.05
     =
    1.02
        
    0.96
    AY
    0.96
    H
    0.95
    EN
    0.93
     -
    0.92
    Activations Density 0.000%

    No Known Activations