© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217599
    Prev
    Next
    INDEX
    Explanations

    Talisman, Roman numeral XL

    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_16_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
     memorials
    0.48
    гар
    0.48
     дописа
    0.46
    ㎖
    0.46
     actinides
    0.45
    銨
    0.45
     ಔಷಧ
    0.45
    বন্ধ
    0.45
    addons
    0.44
    osulf
    0.44
    POSITIVE LOGITS
     to
    0.53
    是
    0.52
    把
    0.51
    A
    0.50
     >
    0.50
     +
    0.49
    Progress
    0.49
     %
    0.48
    I
    0.48
     Field
    0.47
    Activations Density 0.000%

    No Known Activations