© 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. 7325
    Prev
    Next
    INDEX
    Explanations

    WebAssembly (Wasm)

    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
    poč
    2.40
    യാ
    2.26
    ้น
    2.26
    previously
    2.23
     ironically
    2.22
     dispon
    2.19
     мүм
    2.17
    ϙ
    2.17
     стать
    2.14
    యే
    2.13
    POSITIVE LOGITS
     stairs
    2.47
    ме
    2.44
    matical
    2.42
    શન
    2.40
     игру
    2.33
    ة
    2.32
    وك
    2.31
     то
    2.27
     slopes
    2.27
    ressed
    2.26
    Activations Density 0.001%

    No Known Activations