© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3625
    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
    го
    2.02
    ف
    1.96
    is
    1.93
    isasi
    1.79
    веден
    1.68
    őség
    1.68
    ен
    1.60
     painfully
    1.59
    ι
    1.59
    ﻰ
    1.57
    POSITIVE LOGITS
     nhau
    1.76
     spoonful
    1.67
    elementAt
    1.60
    ेक्षा
    1.58
     eyesight
    1.54
    ্র
    1.53
    tober
    1.48
    dateTimePicker
    1.47
    $-\
    1.47
     kisses
    1.45
    Activations Density 0.282%

    No Known Activations