© 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. 8049
    Prev
    Next
    INDEX
    Explanations

    if you'd like

    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
    al
    1.57
    ुष
    1.45
     sağlam
    1.39
    ia
    1.36
     ficar
    1.36
    ínű
    1.35
     adecu
    1.32
    +\
    1.31
     vremena
    1.30
    ית
    1.29
    POSITIVE LOGITS
    kms
    1.39
    𝖚
    1.38
    nier
    1.38
    nies
    1.37
    愎
    1.36
     docket
    1.34
    nw
    1.33
    noc
    1.32
    tsd
    1.31
    mniej
    1.31
    Activations Density 0.046%

    No Known Activations