© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132515
    Prev
    Next
    INDEX
    Explanations

    onnx

    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_6_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
    ה
    1.28
    ש
    1.27
    ين
    1.20
    و
    1.05
    המ
    1.04
    dır
    1.02
    س
    0.96
    일
    0.95
     Mayıs
    0.94
    ো
    0.94
    POSITIVE LOGITS
    ang
    1.01
    ays
    0.96
    backs
    0.87
     忄
    0.87
     Ά
    0.84
    fia
    0.84
     hypothes
    0.82
    boards
    0.82
    ay
    0.82
    ow
    0.81
    Activations Density 0.000%

    No Known Activations