© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157781
    Prev
    Next
    INDEX
    Explanations

    commuter express

    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
    ع
    1.84
    你
    1.57
    د
    1.55
    お
    1.52
    ある
    1.45
    我
    1.45
    ע
    1.43
    ا
    1.42
    ה
    1.39
    า
    1.37
    POSITIVE LOGITS
     for
    1.25
    1.18
    𝐧
    1.04
    t
    0.93
    ong
    0.88
    tım
    0.88
    r
    0.88
    zione
    0.87
    ৬৮
    0.87
    れて
    0.82
    Activations Density 0.000%

    No Known Activations