© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88441
    Prev
    Next
    INDEX
    Explanations

    URL or link in text

    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_23_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
     Tamaño
    0.46
    シティ
    0.45
    gram
    0.45
    größe
    0.45
     サイズ
    0.44
     रिक्वायरमेंट
    0.43
     gram
    0.42
     ಟ
    0.41
     expected
    0.40
    ॉर्क
    0.40
    POSITIVE LOGITS
    ogenetic
    0.41
     incarn
    0.39
     истори
    0.38
     reincarn
    0.38
     prosecute
    0.36
     anima
    0.36
    march
    0.36
     bailar
    0.36
    package
    0.36
    本書
    0.35
    Activations Density 0.001%

    No Known Activations