© 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. 4901
    Prev
    Next
    INDEX
    Explanations

    scientific american computing

    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
    la
    1.35
    ^{*},
    1.24
    ney
    1.23
    dan
    1.21
    цев
    1.19
    ny
    1.17
    nya
    1.17
    ش
    1.11
    なに
    1.10
    li
    1.08
    POSITIVE LOGITS
    יות
    1.41
    ன
    1.33
    Reminder
    1.27
     апреля
    1.21
    মান
    1.21
     harassing
    1.20
    Founded
    1.19
    estructive
    1.18
     المن
    1.18
    ب
    1.18
    Activations Density 0.006%

    No Known Activations