© 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. 6556
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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
    ز
    1.37
    ем
    1.24
    ект
    1.18
     hasattr
    1.16
     sementara
    1.14
    ется
    1.08
    publique
    1.07
     sûr
    1.07
    دة
    1.07
     amico
    1.04
    POSITIVE LOGITS
    йся
    1.29
     lame
    1.25
     صلى
    1.25
    م
    1.23
    োষ
    1.21
     axons
    1.20
     handkerchief
    1.18
    beams
    1.16
    athon
    1.15
    ᅯ
    1.15
    Activations Density 0.011%

    No Known Activations