© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6087
    Prev
    Next
    INDEX
    Explanations

    The Human Experience

    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
     وب
    0.51
    ల
    0.50
    شك
    0.50
    ″
    0.49
    Victory
    0.48
     گیری
    0.47
    其他
    0.47
    vacuum
    0.45
     successor
    0.45
     nenhum
    0.45
    POSITIVE LOGITS
     века
    0.45
     maturities
    0.43
     banknotes
    0.43
    ञ
    0.41
     parasit
    0.40
     infestations
    0.40
    ٿ
    0.40
     arrivé
    0.39
    ший
    0.39
     halinde
    0.39
    Activations Density 0.865%

    No Known Activations