© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9275
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    Interval
    0.64
    interval
    0.61
    Filter
    0.60
    wege
    0.60
    innings
    0.58
    
    0.58
    Filters
    0.57
    retry
    0.57
    Merging
    0.56
    Annot
    0.56
    POSITIVE LOGITS
    “,
    0.83
    ”,
    0.74
    :",
    0.74
     поля
    0.73
    ல்களில்
    0.72
     നടക്കുന്ന
    0.71
     από
    0.71
     как
    0.71
    ",
    0.71
     welche
    0.71
    Activations Density 0.058%

    No Known Activations