© 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. 7914
    Prev
    Next
    INDEX
    Explanations

    interface or place followed by punctuation

    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
    <bos>
    0.68
     wes
    0.63
     koja
    0.61
    الوجی
    0.60
     Перейти
    0.60
    ్రె
    0.60
     lecz
    0.59
     hende
    0.58
    })_{
    0.58
    ới
    0.58
    POSITIVE LOGITS
    ت
    0.69
    𝑖
    0.67
    {
    0.62
    ो
    0.61
    𝑒
    0.59
    的值
    0.57
    ލ
    0.56
    zantine
    0.56
    ために
    0.56
    𝒎
    0.55
    Activations Density 0.551%

    No Known Activations