© 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. 8026
    Prev
    Next
    INDEX
    Explanations

    tangled cables

    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
    y
    3.30
    an
    3.10
    leş
    2.96
    𝑦
    2.49
    jších
    2.47
    ют
    2.46
    addEventListener
    2.37
     ưu
    2.31
     clima
    2.31
    𝑛
    2.31
    POSITIVE LOGITS
    𝗮
    3.24
    𝗻
    3.10
    ą
    3.04
    𝗶
    2.95
    糬
    2.89
     harmonique
    2.88
    \%).
    2.78
    可以看出
    2.69
     deserial
    2.66
    𝗲
    2.66
    Activations Density 0.003%

    No Known Activations