© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9498
    Prev
    Next
    INDEX
    Explanations

    left and right

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    ေသ
    0.63
    afir
    0.63
    愫
    0.62
    
    0.61
     Dang
    0.61
     সংখ্যাগরিষ্ঠ
    0.60
    ͌
    0.59
    ўнай
    0.59
    chner
    0.58
     appréci
    0.58
    POSITIVE LOGITS
     left
    4.62
    Left
    4.19
    left
    4.19
    左
    4.16
     Left
    4.15
    右
    3.81
     LEFT
    3.69
     左
    3.67
    LEFT
    3.63
     right
    3.58
    Activations Density 0.265%

    No Known Activations