© 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. 8726
    Prev
    Next
    INDEX
    Explanations

    expressive

    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
    न
    3.23
    িতে
    2.90
     chunks
    2.85
    ائج
    2.80
    ن
    2.74
    liness
    2.70
     ρο
    2.66
    eritud
    2.63
    个小时
    2.61
     copolymers
    2.61
    POSITIVE LOGITS
    ES
    2.98
    豊かな
    2.78
     والر
    2.77
    𝑭
    2.76
     dụng
    2.69
     flourish
    2.68
    ਸ
    2.65
     confidentialité
    2.64
     adjoint
    2.64
    gleich
    2.63
    Activations Density 0.044%

    No Known Activations