© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211507
    Prev
    Next
    INDEX
    Explanations

    tree of thought

    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_5_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
    м
    1.35
     térm
    1.30
     ficción
    1.29
    of
    1.27
    ુ
    1.27
     práct
    1.26
     médicos
    1.23
     científicos
    1.22
     económicos
    1.21
     cómod
    1.20
    POSITIVE LOGITS
    '
    1.99
     Tree
    1.60
     Trees
    1.44
    "
    1.38
    Tree
    1.36
     trees
    1.31
    \
    1.25
     but
    1.24
    পালা
    1.23
     tree
    1.21
    Activations Density 0.000%

    No Known Activations