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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3504
    Prev
    Next
    INDEX
    Explanations

    MentalHealth.gov links

    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
    에
    2.06
    й
    2.03
    ме
    2.02
    та
    2.02
     avrebbe
    1.96
     altijd
    1.92
     habis
    1.90
     faccio
    1.89
    ный
    1.84
    سلم
    1.83
    POSITIVE LOGITS
    ente
    1.80
    ../../
    1.56
    inside
    1.52
    ">(</
    1.51
    initiated
    1.47
    ադ
    1.47
     हिस्सा
    1.45
    פּ
    1.42
    ларни
    1.41
     navigable
    1.37
    Activations Density 0.002%

    No Known Activations