© 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. 6028
    Prev
    Next
    INDEX
    Explanations

    mathematical, code, or technical terms

    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
     }^{*}
    3.01
     }^{
    2.99
     }^{\
    2.76
     }^{*}$
    2.64
     }^{-
    2.62
     }^{+}$
    2.59
     }^{*
    2.43
    ியாக
    2.32
     denn
    2.31
     }^{+}
    2.29
    POSITIVE LOGITS
    tte
    2.61
    ()=>{
    2.54
    ➢
    2.50
    これ
    2.46
    ০০০
    2.45
    chromosome
    2.39
     hechos
    2.35
    ுங்கள்
    2.35
    
    2.27
    فيف
    2.26
    Activations Density 0.015%

    No Known Activations