© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88367
    Prev
    Next
    INDEX
    Explanations

    say "ate" or "ation"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    0.79
    iya
    0.71
    iot
    0.71
    ी
    0.71
    iat
    0.70
    i
    0.70
    ી
    0.68
    ი
    0.68
    י
    0.67
    ে
    0.63
    POSITIVE LOGITS
    ations
    0.46
    azione
    0.44
     IDS
    0.44
    acion
    0.43
    ation
    0.42
     insertion
    0.42
    atorial
    0.41
    acyjnych
    0.41
    ación
    0.41
    lation
    0.41
    Activations Density 0.000%

    No Known Activations