© 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. 54123
    Prev
    Next
    INDEX
    Explanations

    dried herbs

    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
    釀
    0.41
    ソロ
    0.37
    obuf
    0.36
    HARD
    0.36
    jač
    0.36
     Deals
    0.35
    leden
    0.35
    roar
    0.35
    bump
    0.35
    orov
    0.35
    POSITIVE LOGITS
    ╩
    0.38
    RNA
    0.35
     তাছাড়া
    0.35
     overlapping
    0.34
     Paw
    0.34
     Cul
    0.34
     pursuing
    0.34
    աք
    0.33
    ">–
    0.33
     cul
    0.33
    Activations Density 0.003%

    No Known Activations