© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    traffic, reach, impressions

    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
     slew
    0.48
     montón
    0.46
     whim
    0.46
    딩
    0.45
     retreating
    0.44
     continents
    0.44
     hood
    0.44
     republics
    0.43
    гото
    0.43
    成的
    0.43
    POSITIVE LOGITS
    tidak
    0.57
    ज
    0.55
    argaan
    0.53
    윽
    0.53
    он
    0.52
    dorf
    0.52
    ं
    0.52
    Tidak
    0.51
    dı
    0.50
    ვნ
    0.50
    Activations Density 0.104%

    No Known Activations