© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104773
    Prev
    Next
    INDEX
    Explanations

    scratches

    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_1_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
     for
    1.29
     in
    1.25
    g
    1.20
    d
    1.13
    在
    1.13
    يد
    1.07
    も
    1.02
     by
    0.99
     في
    0.99
    يل
    0.99
    POSITIVE LOGITS
    یم
    1.57
    ่า
    1.48
    સ
    1.29
    к
    1.27
    ن
    1.23
    น
    1.21
    لان
    1.18
    اب
    1.17
    न
    1.11
    ல்
    1.10
    Activations Density 0.001%

    No Known Activations