© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27409
    Prev
    Next
    INDEX
    Explanations

    load in 8bit

    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_40_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
    恆
    0.36
    迲
    0.35
     forces
    0.34
     richard
    0.34
     wardrobes
    0.33
    ucos
    0.33
     Hines
    0.32
     GON
    0.32
     franchise
    0.32
     Filing
    0.32
    POSITIVE LOGITS
     toplant
    0.34
    িস্ট
    0.34
    স্থিত
    0.34
    removeChild
    0.34
     खुफिया
    0.34
    ሱስ
    0.33
    台
    0.33
    形势
    0.33
    사각형
    0.33
    मेर
    0.32
    Activations Density 0.000%

    No Known Activations