© 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. 7407
    Prev
    Next
    INDEX
    Explanations

    family groups

    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
    ل
    2.96
    maket
    2.72
    hasClass
    2.38
    LAGAB
    2.36
    لین
    2.34
    ようだ
    2.32
    er
    2.24
    ię
    2.23
     jati
    2.23
    い
    2.21
    POSITIVE LOGITS
    د
    3.02
    नीय
    2.63
     рода
    2.48
    뮤
    2.46
    깐
    2.44
     hutan
    2.38
    ше
    2.36
     danni
    2.29
     prenn
    2.28
     subtilis
    2.28
    Activations Density 0.001%

    No Known Activations