© 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. 34985
    Prev
    Next
    INDEX
    Explanations

    Information Retrieval

    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
     prioritize
    0.66
    ↵
    0.60
     strony
    0.59
    ில்
    0.57
     roughly
    0.57
     administer
    0.56
    িয়ে
    0.55
     demonstrate
    0.55
     TIME
    0.55
     ожида
    0.54
    POSITIVE LOGITS
    ia
    0.68
    的
    0.66
    ہ
    0.66
    3
    0.65
    的和
    0.65
    2
    0.63
    فت
    0.61
    smtb
    0.61
     militari
    0.60
    hattim
    0.60
    Activations Density 0.005%

    No Known Activations