© 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. 1486
    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
    rinsim
    0.87
     supposing
    0.86
    न
    0.84
     Waalaikumsalam
    0.81
    राधिक
    0.79
    ◠
    0.78
    EnumValue
    0.78
    ुलम
    0.76
    rangian
    0.76
    samp
    0.76
    POSITIVE LOGITS
     necesariamente
    0.70
    $&
    0.68
    적으로
    0.67
     exud
    0.64
    Denote
    0.63
     arada
    0.62
     decentral
    0.61
    лары
    0.60
    යන්
    0.60
    vskip
    0.59
    Activations Density 0.636%

    No Known Activations