© 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. 80411
    Prev
    Next
    INDEX
    Explanations

    "a" followed by sizes or qualities

    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
     Coop
    0.37
    ankt
    0.35
     Minneapolis
    0.35
    ldecode
    0.35
     colleagues
    0.34
    umin
    0.34
    演
    0.34
    椅
    0.34
     rời
    0.33
     tiến
    0.33
    POSITIVE LOGITS
    Sage
    0.39
     લાગ
    0.37
    ურთ
    0.36
    çuk
    0.36
    upload
    0.36
    Upload
    0.35
    Relevant
    0.35
    private
    0.35
    OTO
    0.35
     맞
    0.35
    Activations Density 0.000%

    No Known Activations