© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46808
    Prev
    Next
    INDEX
    Explanations

    types of trees

    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
    ق
    0.54
    ين
    0.52
    ен
    0.52
    n
    0.51
     selepas
    0.48
     cartoon
    0.47
    ுள்ள
    0.45
    ﻖ
    0.45
    cartoon
    0.45
    ан
    0.44
    POSITIVE LOGITS
     rừng
    0.57
     poplar
    0.56
     Trees
    0.55
     Bamboo
    0.52
     વૃક્ષ
    0.52
    AvlTree
    0.52
     realiz
    0.51
    senz
    0.51
    🪵
    0.51
     Like
    0.51
    Activations Density 0.027%

    No Known Activations