© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2950
    Prev
    Next
    INDEX
    Explanations

    whole grains or fullscreen

    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_40_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
    िनय
    0.38
     biber
    0.35
    arder
    0.35
    摫
    0.35
     controlado
    0.34
     Proctor
    0.34
    suffixes
    0.33
    }+\
    0.33
    얹
    0.33
     CUT
    0.33
    POSITIVE LOGITS
     full
    1.85
     Full
    1.78
    Full
    1.70
     fullscreen
    1.62
    full
    1.57
     FULL
    1.53
    Fullscreen
    1.48
    FullScreen
    1.46
    FULL
    1.45
    fullscreen
    1.41
    Activations Density 0.101%

    No Known Activations