© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5985
    Prev
    Next
    INDEX
    Explanations

    how to or how"s"

    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_39_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
     sintered
    0.43
    spinlock
    0.42
    guess
    0.39
     diagn
    0.38
    ")->
    0.38
     shin
    0.38
    )$-
    0.37
    defeat
    0.37
     corona
    0.37
     derrota
    0.36
    POSITIVE LOGITS
    アウトドア
    0.40
    üten
    0.40
     переменную
    0.39
    Roberto
    0.38
    パール
    0.38
    Ⲕ
    0.38
    注明
    0.38
    在日本
    0.36
    强大
    0.36
    ysteine
    0.36
    Activations Density 0.000%

    No Known Activations