© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5073
    Prev
    Next
    INDEX
    Explanations

    cat, thick

    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_38_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
    尹
    0.44
    yukur
    0.42
    資訊
    0.40
    uliert
    0.40
    祟
    0.38
    裁剪
    0.37
     consect
    0.37
    ()}")
    0.37
    淌
    0.37
    alignat
    0.36
    POSITIVE LOGITS
     thick
    0.50
     cat
    0.48
    猫
    0.44
     Thick
    0.43
     Rob
    0.42
    薄
    0.42
     dom
    0.41
     Cat
    0.41
     differentiated
    0.41
     cats
    0.41
    Activations Density 0.010%

    No Known Activations