© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 905
    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_12_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
     articulate
    0.50
     каждая
    0.49
     Seasonal
    0.49
     incarcer
    0.49
     robbing
    0.48
     ambigu
    0.47
     ئەم
    0.46
     路
    0.46
     amends
    0.46
     restring
    0.45
    POSITIVE LOGITS
    Standard
    0.39
    国民
    0.38
    ]%
    0.37
    मंत्र
    0.36
    ীতি
    0.34
    iftung
    0.34
    ほ
    0.34
    сле
    0.33
    Direct
    0.33
    引き続き
    0.33
    Activations Density 0.001%

    No Known Activations