© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110077
    Prev
    Next
    INDEX
    Explanations

    nesting

    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
    ের
    1.49
    3
    1.48
    ی
    1.47
    4
    1.23
    s
    1.19
    ปี
    1.17
    ы
    1.17
    6
    1.16
    ۔
    1.16
    ς
    1.13
    POSITIVE LOGITS
     a
    1.52
    न
    1.35
    ag
    1.28
    an
    1.24
    리
    1.23
    res
    1.21
    ens
    1.19
    ay
    1.16
    स्पति
    1.11
    ن
    1.09
    Activations Density 0.000%

    No Known Activations