© 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. 109805
    Prev
    Next
    INDEX
    Explanations

    CAD software, data, and design tasks

    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
    are
    1.57
    ل
    1.47
    d
    1.35
    p
    1.31
    с
    1.28
    л
    1.24
    س
    1.21
    ani
    1.20
    ne
    1.18
    ning
    1.18
    POSITIVE LOGITS
    ט
    1.16
    ม
    1.11
    ב
    1.09
    נ
    1.09
    ض
    1.09
     cataly
    1.05
    र
    1.03
    يد
    1.00
    は
    1.00
    은
    0.99
    Activations Density 0.001%

    No Known Activations