© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217370
    Prev
    Next
    INDEX
    Explanations

    floral tube surrounding

    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_16_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
    halle
    0.50
    h
    0.48
    hale
    0.47
     الك
    0.46
    HAD
    0.46
    hard
    0.46
    sidebar
    0.46
    栉
    0.45
    at
    0.44
    用户名
    0.44
    POSITIVE LOGITS
     uttering
    0.51
     evid
    0.48
    ,»
    0.48
    を楽し
    0.46
    ょ
    0.46
     appContext
    0.46
    表現
    0.45
    言語
    0.45
     presion
    0.44
    個別
    0.44
    Activations Density 0.000%

    No Known Activations