© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141695
    Prev
    Next
    INDEX
    Explanations

    code operations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    vency
    0.39
    {#
    0.38
    ülés
    0.37
     indexBuffer
    0.36
     വിവിധ
    0.36
    imsy
    0.36
     tiens
    0.36
     மணிக்கு
    0.36
     ****",
    0.35
    ตรี
    0.35
    POSITIVE LOGITS
     praises
    0.36
     rattles
    0.34
     alternating
    0.34
     Algar
    0.34
     Аль
    0.33
    landmarks
    0.33
     reviews
    0.32
    Аль
    0.32
     rep
    0.32
     đâu
    0.32
    Activations Density 0.001%

    No Known Activations