© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79525
    Prev
    Next
    INDEX
    Explanations

    partner relationships

    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_0_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
    的部分
    1.43
    能
    1.43
    il
    1.40
    ين
    1.40
    اري
    1.35
    chaft
    1.34
    يد
    1.31
    的光
    1.30
    的能力
    1.29
    ul
    1.28
    POSITIVE LOGITS
    ।
    1.99
    s
    1.43
    ні
    1.41
    لی
    1.34
    speople
    1.27
    ン
    1.24
    یی
    1.22
    si
    1.21
    ν
    1.21
    स
    1.20
    Activations Density 0.000%

    No Known Activations