© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246201
    Prev
    Next
    INDEX
    Explanations

    header and sticky elements

    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
     অশ্র
    0.37
     Agricultura
    0.35
    क्साइड
    0.32
     Bundle
    0.32
    农业
    0.32
     digoxin
    0.32
     pu
    0.32
    >¯</
    0.32
    𒀯
    0.32
     गोल
    0.32
    POSITIVE LOGITS
     sticking
    1.04
     stuck
    1.02
     sticky
    1.02
    Sticky
    0.94
    sticky
    0.91
     stick
    0.88
     Sticky
    0.87
    Stick
    0.79
    stick
    0.77
     Stick
    0.77
    Activations Density 0.003%

    No Known Activations