© 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. 3669
    Prev
    Next
    INDEX
    Explanations

    tic-tac-toe

    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
     kürz
    0.63
    a
    0.56
     захи
    0.55
     müş
    0.55
    QString
    0.54
     зокрема
    0.54
    া
    0.53
    री
    0.53
     Lately
    0.53
    ħ
    0.52
    POSITIVE LOGITS
     endast
    0.55
    ங்கிணை
    0.51
    day
    0.50
    باشد
    0.49
     cotidiana
    0.49
    zelfde
    0.48
     equivalently
    0.48
    别
    0.48
    Capabilities
    0.47
    lap
    0.47
    Activations Density 0.005%

    No Known Activations