© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53102
    Prev
    Next
    INDEX
    Explanations

    log activity details

    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_31_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
    精度
    0.43
     rayons
    0.41
     Accuracy
    0.41
    TES
    0.40
     +/-
    0.38
     accuracy
    0.38
     progetto
    0.38
     ஆராய்ச்சிய
    0.38
    䪲
    0.38
    abspath
    0.37
    POSITIVE LOGITS
     organisational
    0.40
     počas
    0.39
    вец
    0.38
    राम
    0.36
    आम
    0.35
    vit
    0.35
    남도
    0.35
     centimetres
    0.34
     ут
    0.33
    ServiceName
    0.33
    Activations Density 0.007%

    No Known Activations