© 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. 5744
    Prev
    Next
    INDEX
    Explanations

    code blocks and mathematical notation

    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
    ➢
    3.16
    ০০০
    2.88
    ()=>{
    2.87
    tte
    2.87
    ка
    2.84
    zeug
    2.84
    dürü
    2.79
    これ
    2.77
    ด์
    2.68
    chromosome
    2.64
    POSITIVE LOGITS
     }^{*}
    3.58
     }^{
    3.58
     }^{\
    3.20
     }^{*
    2.96
     }^{-
    2.96
     }^{*}$
    2.93
     }^{+}$
    2.75
     CuSO
    2.71
    وية
    2.69
     }_{
    2.63
    Activations Density 0.058%

    No Known Activations