© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18188
    Prev
    Next
    INDEX
    Explanations

    family history and online archives

    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_40_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
    骑士
    0.41
    球迷
    0.41
    扇
    0.38
    팬
    0.37
     ขาย
    0.36
    の位置
    0.35
    proof
    0.35
    丈
    0.35
     डिवाइड
    0.35
    ファン
    0.35
    POSITIVE LOGITS
     website
    0.52
     Бон
    0.43
    website
    0.42
     roots
    0.42
     free
    0.40
     Ó
    0.40
    roots
    0.40
     batch
    0.39
     Gen
    0.39
     Website
    0.39
    Activations Density 0.000%

    No Known Activations