© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6723
    Prev
    Next
    INDEX
    Explanations

    list item markers, definitions

    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
    ר
    0.81
     冖
    0.68
    ભ
    0.66
     Flav
    0.61
    NUMX
    0.61
     bhave
    0.60
     וע
    0.60
    ก่
    0.60
     yad
    0.60
    怙
    0.59
    POSITIVE LOGITS
    খানেই
    0.65
    sächlich
    0.63
    pesar
    0.62
    ^{\
    0.61
     EGF
    0.61
    .\\
    0.61
     columnIndex
    0.61
    >.
    0.60
    ឧបករណ៍
    0.59
    менно
    0.59
    Activations Density 1.002%

    No Known Activations