© 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. 7280
    Prev
    Next
    INDEX
    Explanations

    product information and development

    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
    ⏤
    1.21
    
    1.09
    ⠉
    1.08
    ∼
    1.06
     paginate
    1.05
    ⿳
    1.05
    𝑆
    1.04
    𝑢
    1.04
     virtue
    1.03
     TDC
    1.03
    POSITIVE LOGITS
    fonte
    1.13
    requis
    1.10
    אס
    1.06
    lü
    1.05
     kembali
    1.05
    ف
    1.04
    皇
    0.99
     ehemal
    0.99
    ově
    0.98
     apareció
    0.97
    Activations Density 0.024%

    No Known Activations