© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259616
    Prev
    Next
    INDEX
    Explanations

    mapping types and relationships

    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_22_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
    0.44
    ˙
    0.44
     ан
    0.42
    data
    0.42
    de
    0.41
    AB
    0.41
    df
    0.41
    dates
    0.39
     hastened
    0.39
    i
    0.38
    POSITIVE LOGITS
     Cumber
    0.49
     Triathlon
    0.49
     Sovi
    0.48
    वां
    0.47
    enciar
    0.46
     IAAF
    0.46
     FEI
    0.46
    𒆪
    0.45
    hattim
    0.45
     Butterfly
    0.45
    Activations Density 0.000%

    No Known Activations