© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173990
    Prev
    Next
    INDEX
    Explanations

    made of

    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_20_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
    est
    0.31
    acet
    0.28
    prop
    0.28
    jets
    0.28
    test
    0.28
    goat
    0.28
     ?
    0.27
    itle
    0.27
     Mg
    0.27
    O
    0.27
    POSITIVE LOGITS
    跶
    0.30
    创建一个
    0.27
    смотрим
    0.27
     ZR
    0.26
     sadistic
    0.25
    venu
    0.24
    munk
    0.24
     oldCount
    0.24
    <unused1094>
    0.24
    вей
    0.23
    Activations Density 0.002%

    No Known Activations