© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77642
    Prev
    Next
    INDEX
    Explanations

    environment variables

    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
     Stan
    0.43
    Stan
    0.43
     सेक
    0.42
    侈
    0.40
     pand
    0.39
    တင်
    0.37
    sType
    0.37
     રીતે
    0.37
     हीट
    0.37
    ܙ
    0.37
    POSITIVE LOGITS
     harassed
    0.39
     الحم
    0.36
    inductive
    0.35
    катери
    0.35
     Epilepsy
    0.35
    ἁ
    0.34
    include
    0.34
    ('\
    0.34
     follic
    0.34
    Quadr
    0.34
    Activations Density 0.003%

    No Known Activations