© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13734
    Prev
    Next
    INDEX
    Explanations

    arms, shoulders, elbows

    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_13_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
    ne
    0.58
    we
    0.54
     newspapers
    0.53
    ke
    0.52
     liens
    0.52
     ރ
    0.52
     नाते
    0.52
     perist
    0.52
    නු
    0.50
     नीम
    0.50
    POSITIVE LOGITS
    ż
    0.54
    牧
    0.49
    萨
    0.45
    作为
    0.45
    )\,
    0.45
    Tá
    0.44
     hingga
    0.43
     şeh
    0.43
    Tar
    0.43
    árd
    0.43
    Activations Density 0.042%

    No Known Activations