© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2941
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline

    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_5_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
     sare
    0.71
    ieß
    0.59
     tuh
    0.58
    iate
    0.57
    -\
    0.57
    לט
    0.57
     образу
    0.57
    ০০
    0.56
    mav
    0.56
     acidosis
    0.56
    POSITIVE LOGITS
     reputations
    0.78
     concomit
    0.76
     protracted
    0.74
    ʟ
    0.73
    ﻮ
    0.73
    𝐥
    0.72
    cknowled
    0.72
     crankshaft
    0.72
    criar
    0.71
     dată
    0.71
    Activations Density 0.006%

    No Known Activations