© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1909
    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_2_width_16k_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
    ような
    2.03
    ように
    1.88
    িক
    1.88
     nectar
    1.88
    
    1.83
    le
    1.80
    ឹម
    1.80
     bine
    1.78
    
    1.78
    ร์
    1.76
    POSITIVE LOGITS
    }))
    1.77
    BTW
    1.76
    InvalidArgument
    1.75
     allegiance
    1.67
    Measurements
    1.66
     যাইহোক
    1.66
    Р
    1.61
     Administrative
    1.61
     tangente
    1.58
     Remarks
    1.57
    Activations Density 0.000%

    No Known Activations