© 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. 8373
    Prev
    Next
    INDEX
    Explanations

    to maintain, stabilize, keep

    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
    ا
    2.13
    𝐤
    2.09
    जनक
    2.07
    и
    2.05
    listof
    2.01
    𝐭
    1.99
    lou
    1.94
    grasp
    1.92
    ที่
    1.91
    에
    1.89
    POSITIVE LOGITS
    ages
    2.29
    нице
    2.06
    ница
    1.96
    א
    1.94
    את
    1.89
    あ
    1.80
    ény
    1.76
    ethyl
    1.74
    ண்டு
    1.74
    ittal
    1.72
    Activations Density 0.015%

    No Known Activations