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

    Neuronpedia

    Jacobian LensNEW
    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. 6602
    Prev
    Next
    INDEX
    Explanations

    excel, flourish, thrive

    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
    ු
    0.78
    tura
    0.72
    oną
    0.71
    ak
    0.70
    apai
    0.69
     incoherent
    0.68
    ierungen
    0.68
    εται
    0.68
    おく
    0.68
    tive
    0.68
    POSITIVE LOGITS
    ()=>{
    0.80
    الت
    0.73
     веке
    0.73
    原因
    0.67
     вопро
    0.67
    Trước
    0.65
     nakon
    0.65
     включа
    0.64
    newNode
    0.64
    Пла
    0.64
    Activations Density 0.304%

    No Known Activations