© 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. 7266
    Prev
    Next
    INDEX
    Explanations

    Yokohama URLs

    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
    ನ
    2.43
     reluctance
    2.41
    jakan
    2.39
    ά
    2.28
     годов
    2.28
     annoyance
    2.27
    쾨
    2.26
    selves
    2.24
    EDULE
    2.23
     коже
    2.20
    POSITIVE LOGITS
    вропей
    2.73
     cuales
    2.53
    
    2.47
    
    2.47
    pte
    2.46
     luego
    2.44
    𝘮
    2.42
    нде
    2.37
     mite
    2.34
     buah
    2.34
    Activations Density 0.000%

    No Known Activations