© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92563
    Prev
    Next
    INDEX
    Explanations

    fl

    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_60_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
    獐
    0.49
     perfected
    0.42
    дили
    0.40
    dul
    0.40
    داً
    0.40
    ණය
    0.39
     carénés
    0.39
     PATENT
    0.39
    𝚍
    0.38
     FIB
    0.38
    POSITIVE LOGITS
    i
    0.91
    ي
    0.69
    ി
    0.60
    ière
    0.59
    يّ
    0.58
    ierten
    0.57
    ி
    0.57
    iest
    0.56
    ి
    0.56
    iş
    0.55
    Activations Density 0.000%

    No Known Activations