© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3737
    Prev
    Next
    INDEX
    Explanations

    accuracy estimation

    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_39_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
    FBSDKApp
    0.38
    rowse
    0.32
    ColorF
    0.32
     మొ
    0.31
    䒠
    0.31
    Callbacks
    0.31
    Bread
    0.30
    麵
    0.30
     முக
    0.30
    fera
    0.30
    POSITIVE LOGITS
     accurate
    0.56
    准确
    0.52
     accuracy
    0.48
    accurate
    0.47
     Accurate
    0.47
     dokład
    0.44
     accurately
    0.41
     точно
    0.40
     정확
    0.40
     accuracies
    0.40
    Activations Density 0.000%

    No Known Activations