© 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. 7274
    Prev
    Next
    INDEX
    Explanations

    javascript array reduce

    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
     µ
    2.64
    ಖ
    2.34
    愿
    2.26
     isLoading
    2.18
    reply
    2.16
    polo
    2.11
     borderRadius
    2.09
    vyš
    2.09
     muon
    2.08
    ⎯
    2.08
    POSITIVE LOGITS
    ی
    2.59
    в
    2.49
    đ
    2.30
    ി
    2.29
    েক
    2.23
     linestyle
    2.02
    i
    2.01
    Đ
    1.98
    д
    1.96
    ውነ
    1.95
    Activations Density 0.001%

    No Known Activations