© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36251
    Prev
    Next
    INDEX
    Explanations

    code blocks and output

    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
    ၻ
    0.33
     duplicates
    0.32
    澫
    0.30
    ᓪ
    0.30
    gült
    0.30
     Pont
    0.30
    䢀
    0.29
     ۾
    0.28
     ગ્ર
    0.28
     клет
    0.28
    POSITIVE LOGITS
     cy
    0.32
    各类
    0.32
    zek
    0.30
    വിത
    0.30
    adam
    0.29
    prescription
    0.28
     скри
    0.28
    cp
    0.28
    sig
    0.28
    უბ
    0.28
    Activations Density 0.018%

    No Known Activations