© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29868
    Prev
    Next
    INDEX
    Explanations

    written reports, author names

    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_10_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
    ৮
    0.45
    จาก
    0.43
     dh
    0.43
    ான்
    0.42
    ouin
    0.42
     D
    0.40
    पे
    0.40
    Princ
    0.40
    หลัก
    0.40
    е
    0.40
    POSITIVE LOGITS
     рис
    0.55
    refs
    0.55
    ീഷ
    0.51
    TL
    0.49
    ፈጥ
    0.48
    人と
    0.48
    yers
    0.47
     corroborate
    0.47
     ರೂ
    0.47
    reports
    0.46
    Activations Density 0.000%

    No Known Activations