© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219000
    Prev
    Next
    INDEX
    Explanations

    sign or commit to something

    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_31_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
     crushing
    0.36
     shattering
    0.35
    飆
    0.34
    augh
    0.33
    Mills
    0.32
     attentive
    0.32
     exhibition
    0.32
     Mills
    0.32
     Exhibition
    0.32
    ải
    0.31
    POSITIVE LOGITS
     Signed
    0.38
     surrender
    0.38
    дове
    0.37
     DMBT
    0.36
     अधू
    0.36
    ندگی
    0.35
    륵
    0.34
    DOF
    0.34
    apers
    0.34
     blij
    0.34
    Activations Density 0.001%

    No Known Activations