© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7490
    Prev
    Next
    INDEX
    Explanations

    travel, hotels, departments, places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
     gameObject
    0.78
    分页
    0.65
    𝐄
    0.64
    forEach
    0.63
     entero
    0.61
    await
    0.61
    LQ
    0.61
    ర్రీ
    0.59
    साइटी
    0.58
    NK
    0.58
    POSITIVE LOGITS
    an
    0.84
    o
    0.75
    ه
    0.72
    a
    0.71
    ল
    0.68
    on
    0.68
    т
    0.65
    ம்
    0.64
    ار
    0.63
    й
    0.63
    Activations Density 0.031%

    No Known Activations