© 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. 1610
    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
    vens
    3.04
    cans
    2.91
    о
    2.89
    יו
    2.89
    ு
    2.78
    ీల
    2.77
    ﻲ
    2.69
     purported
    2.66
    ುವ
    2.64
     Vamos
    2.62
    POSITIVE LOGITS
    ゥ
    3.95
     Bxd
    3.76
    ଼
    3.68
    olph
    3.59
    yllic
    3.48
    ោះស្រាយ
    3.45
    ding
    3.43
    ependent
    3.28
    der
    3.25
    DING
    3.15
    Activations Density 0.429%

    No Known Activations