© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138461
    Prev
    Next
    INDEX
    Explanations

    news channels

    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_46_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
    टक
    0.42
     Tu
    0.41
     On
    0.39
     tu
    0.39
     Ide
    0.37
    elius
    0.37
    碍
    0.37
     meio
    0.36
    途
    0.36
     ту
    0.36
    POSITIVE LOGITS
    ಷ್ಯ
    0.47
    Fry
    0.42
    啫
    0.38
    麂
    0.38
     ऋषभ
    0.36
     Zeiss
    0.36
    
    0.35
    리즈
    0.35
     gravitation
    0.35
     Wittgenstein
    0.35
    Activations Density 0.000%

    No Known Activations