© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106639
    Prev
    Next
    INDEX
    Explanations

    Solomon

    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_1_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
    o
    1.34
    n
    1.32
    a
    1.16
    d
    1.06
    ing
    1.04
    is
    1.01
    u
    1.00
    x
    0.97
    áty
    0.96
    ంబేద్కర్
    0.94
    POSITIVE LOGITS
    '
    1.28
    {
    1.27
    ור
    1.18
    צ
    1.13
    ку
    1.08
    2
    1.05
    י
    1.05
    м
    1.04
    み
    1.02
    ،
    0.99
    Activations Density 0.000%

    No Known Activations