© 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. 8276
    Prev
    Next
    INDEX
    Explanations

    tell me: What

    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
    quela
    2.68
    ت
    2.51
     impair
    2.37
    꼐
    2.36
    año
    2.24
    
    2.22
    ارات
    2.20
    то
    2.19
    enrich
    2.19
    с
    2.19
    POSITIVE LOGITS
    বাহী
    2.72
    ../
    2.65
    𝗢
    2.60
    ১
    2.54
    𝗔
    2.49
    ik
    2.48
    𝗦
    2.46
    𝗡
    2.42
    𝗜
    2.40
    le
    2.39
    Activations Density 0.019%

    No Known Activations