© 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. 7166
    Prev
    Next
    INDEX
    Explanations

    web development tools/frameworks

    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
     Edd
    0.42
    戟
    0.40
    殳
    0.40
     SDI
    0.40
    Shape
    0.39
     Markdown
    0.37
    媢
    0.37
    Px
    0.37
     Daerah
    0.37
     ماين
    0.37
    POSITIVE LOGITS
    /**/*.{
    0.39
    治
    0.39
    никам
    0.38
     waiting
    0.38
    atosis
    0.37
     interfere
    0.37
     reside
    0.36
     chat
    0.36
     rotate
    0.36
     reuniones
    0.36
    Activations Density 0.002%

    No Known Activations