© 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. 4862
    Prev
    Next
    INDEX
    Explanations

    baccarat or Barack

    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
     clav
    1.73
    ে
    1.70
     बताने
    1.65
    ೀವ
    1.55
     innymi
    1.55
     difficult
    1.54
    ه
    1.53
    ิน
    1.52
    ść
    1.52
     bian
    1.52
    POSITIVE LOGITS
    an
    1.76
    is
    1.76
    est
    1.73
    h
    1.67
    hg
    1.56
    しかも
    1.55
    fas
    1.45
    😂😂
    1.44
    a
    1.38
    pire
    1.38
    Activations Density 0.003%

    No Known Activations