© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84264
    Prev
    Next
    INDEX
    Explanations

    sharp angles and descriptions

    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_0_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
    h
    1.72
    hx
    1.43
    ри
    1.40
    1
    1.33
    childComplexity
    1.30
    ૧
    1.30
    lardan
    1.29
    capitalize
    1.28
    column
    1.27
    ᱑
    1.27
    POSITIVE LOGITS
    ка
    1.38
    ك
    1.34
    ン
    1.29
    ure
    1.25
    un
    1.23
    os
    1.19
    ía
    1.19
    ن
    1.19
    ่
    1.16
    um
    1.16
    Activations Density 0.002%

    No Known Activations