© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107132
    Prev
    Next
    INDEX
    Explanations

    Lent, Lentil, Lent bumps

    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_2_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
    ра
    1.62
    ва
    1.26
    お金
    1.24
    した
    1.19
    ח
    1.19
    できる
    1.15
     مي‌
    1.13
    お知らせ
    1.13
     două
    1.13
     rozwiąz
    1.12
    POSITIVE LOGITS
    '
    1.59
    ages
    1.27
    ians
    1.25
     innovations
    1.19
    ettes
    1.16
    naires
    1.16
    gh
    1.16
     opinions
    1.16
    usions
    1.14
     impediments
    1.14
    Activations Density 0.000%

    No Known Activations