© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122879
    Prev
    Next
    INDEX
    Explanations

    `Id` and words ending in `ital`

    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_3_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
    ي
    1.19
    i
    1.12
    ে
    0.89
    ة
    0.89
    י
    0.76
     stehen
    0.72
     deplorable
    0.70
    в
    0.66
    ి
    0.66
    ಿ
    0.66
    POSITIVE LOGITS
     as
    0.84
    pizza
    0.75
     합
    0.73
    り
    0.71
     ک
    0.71
     외
    0.71
    time
    0.70
    elliptic
    0.70
    ↵↵
    0.69
    ری
    0.68
    Activations Density 0.000%

    No Known Activations