© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12836
    Prev
    Next
    INDEX
    Explanations

    notably examples

    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_13_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
    用に
    0.60
    ia
    0.52
     Pools
    0.48
    fj
    0.46
    fear
    0.46
    ir
    0.45
     ನ
    0.45
    Ր
    0.45
    canny
    0.45
    fr
    0.45
    POSITIVE LOGITS
     incluindo
    0.57
    ética
    0.55
     giallo
    0.52
    ajima
    0.52
     botas
    0.52
    Kako
    0.52
     scissor
    0.51
     magenta
    0.50
     dominant
    0.49
     quarto
    0.48
    Activations Density 0.025%

    No Known Activations