© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18357
    Prev
    Next
    INDEX
    Explanations

    UI components

    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_15_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
    压缩
    0.47
    ก่อน
    0.46
    /
    0.46
    าร
    0.46
    ดำเนิน
    0.45
    "
    0.45
    改变
    0.45
    Datum
    0.45
    时代
    0.44
     Lage
    0.43
    POSITIVE LOGITS
     [§
    0.55
     মু
    0.53
    namefont
    0.51
     seen
    0.50
    clinical
    0.50
     വ്യക്ത
    0.50
     matchups
    0.50
     clínicas
    0.50
     нови
    0.50
    njih
    0.50
    Activations Density 0.008%

    No Known Activations