© 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. 2971
    Prev
    Next
    INDEX
    Explanations

    rate changes

    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
     tendencia
    0.37
    跡
    0.36
     tendency
    0.35
    早
    0.34
    theless
    0.34
    迹
    0.34
     trend
    0.33
    郊
    0.33
     unstoppable
    0.33
     SKSpriteNode
    0.33
    POSITIVE LOGITS
    accom
    0.39
     भुव
    0.38
    납
    0.37
    CHT
    0.36
    max
    0.36
    settes
    0.36
     Brug
    0.35
     napi
    0.34
     Variance
    0.34
    钏
    0.34
    Activations Density 0.136%

    No Known Activations