© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78270
    Prev
    Next
    INDEX
    Explanations

    Irish Scottish Gaelic

    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_53_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
    莓
    0.39
     ס
    0.39
    odar
    0.38
     bush
    0.38
    scre
    0.37
     ssid
    0.37
     রু
    0.36
     sinn
    0.36
    烽
    0.36
     stations
    0.35
    POSITIVE LOGITS
     trebalo
    0.41
    Thro
    0.41
    APAC
    0.40
    amano
    0.40
    heira
    0.38
     besitzen
    0.38
    qh
    0.38
     строку
    0.37
     Sham
    0.36
    職業
    0.36
    Activations Density 0.000%

    No Known Activations