© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7677
    Prev
    Next
    INDEX
    Explanations

    Blickfang

    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
     Giordano
    0.40
    း
    0.38
    odyne
    0.38
     dans
    0.37
     Intra
    0.36
    澫
    0.36
     Handwriting
    0.35
     置
    0.35
    бліоте
    0.34
     Chi
    0.34
    POSITIVE LOGITS
     Highlight
    0.57
    highlight
    0.57
    Highlight
    0.56
     highlight
    0.53
     Highlights
    0.46
    HIGHLIGHT
    0.44
    Highlights
    0.42
    Highlighted
    0.41
    highlights
    0.39
     highlighted
    0.39
    Activations Density 0.030%

    No Known Activations