© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5522
    Prev
    Next
    INDEX
    Explanations

    python code import keywords

    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
     }^{
    3.46
     }^{*}
    3.32
     }^{-
    3.05
     }^{\
    2.99
     }^{*}$
    2.82
     }^{*
    2.77
     }^{+}$
    2.74
     }^{+}
    2.60
     }^{[
    2.57
     }_{
    2.56
    POSITIVE LOGITS
    tte
    3.00
    ()=>{
    2.89
    ➢
    2.72
    これ
    2.60
    ০০০
    2.59
    
    2.47
    นี่
    2.46
    dürü
    2.45
    ка
    2.44
     hechos
    2.40
    Activations Density 0.051%

    No Known Activations