© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4881
    Prev
    Next
    INDEX
    Explanations

    StringIO() around strings/data

    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
    onesome
    0.72
    toaster
    0.70
    BUS
    0.69
     vode
    0.67
    𝒟
    0.65
    redient
    0.64
    𝕥
    0.64
    ۃ
    0.63
    redients
    0.63
    ∈
    0.62
    POSITIVE LOGITS
    ни
    0.71
    र
    0.69
     acre
    0.63
    ال
    0.61
    кры
    0.60
    ین
    0.60
     uno
    0.59
    worldly
    0.59
    на
    0.58
     нещо
    0.57
    Activations Density 0.003%

    No Known Activations