© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26211
    Prev
    Next
    INDEX
    Explanations

    forests, trees, bosques

    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_10_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
    ()
    0.73
    on
    0.70
    ilor
    0.68
    vať
    0.68
    (
    0.67
    流动
    0.66
    ༢
    0.65
    9
    0.65
    тивность
    0.64
    
    0.64
    POSITIVE LOGITS
     forest
    1.39
     Forest
    1.26
     tree
    1.23
    Forest
    1.22
     FOREST
    1.12
    א
    1.12
     forests
    1.08
     Tree
    1.01
     дерева
    1.01
    forest
    0.96
    Activations Density 0.032%

    No Known Activations