© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60153
    Prev
    Next
    INDEX
    Explanations

    actually defining or clarifying

    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
    (
    1.55
     be
    1.34
    ين
    1.29
    ви
    1.26
    یم
    1.26
    ా
    1.19
    یس
    1.16
    ر
    1.15
    ور
    1.14
    رسی
    1.14
    POSITIVE LOGITS
     on
    1.53
    д
    1.53
    st
    1.30
    .
    1.13
    c
    1.10
    ts
    1.09
    لا
    1.02
    v
    0.99
    ’.
    0.94
    ş
    0.93
    Activations Density 0.000%

    No Known Activations