© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239480
    Prev
    Next
    INDEX
    Explanations

    describing sensory characteristics

    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_25_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
    initializing
    0.40
    unused
    0.40
    elan
    0.37
     initializing
    0.37
     {
    0.36
    蕴
    0.35
    BV
    0.35
     erud
    0.35
     resetButton
    0.35
     bonita
    0.35
    POSITIVE LOGITS
    旪
    0.40
     любые
    0.39
     komplet
    0.38
     ගැ
    0.38
     masalah
    0.37
    腖
    0.37
    咊
    0.36
     عدة
    0.36
     వచ్చే
    0.36
     紅
    0.36
    Activations Density 0.000%

    No Known Activations