© 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. 151876
    Prev
    Next
    INDEX
    Explanations

    beginning of month

    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
    Into
    0.38
    USE
    0.37
    `
    0.36
    Component
    0.36
    魅力
    0.36
    Invocation
    0.36
     क्वेश्चन
    0.35
    Eligibility
    0.35
    Maintain
    0.35
    邀請
    0.35
    POSITIVE LOGITS
    nikov
    0.41
     ढ
    0.38
    ច្រ
    0.38
    èbres
    0.38
     незале
    0.37
    ફે
    0.37
     σχετικά
    0.36
    চের
    0.36
    するという
    0.36
    រួម
    0.35
    Activations Density 0.002%

    No Known Activations