© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7880
    Prev
    Next
    INDEX
    Explanations

    scale, size, nature

    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
    kais
    0.78
     maj
    0.73
    𝒋
    0.73
    𝒎
    0.72
    kaj
    0.72
    ﺡ
    0.72
    şık
    0.72
     précie
    0.72
    𝒔
    0.72
     chairperson
    0.72
    POSITIVE LOGITS
    ly
    0.78
    LY
    0.68
    )=>{
    0.67
    ت
    0.65
    edad
    0.60
    Се
    0.59
    isVisible
    0.59
    ity
    0.59
     इनमें
    0.58
    AH
    0.58
    Activations Density 0.705%

    No Known Activations