© 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. 3783
    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
     roomy
    1.38
     resembled
    1.31
     supernatants
    1.27
     resembles
    1.23
    に
    1.21
     frm
    1.20
     वहीं
    1.16
     имеется
    1.16
     sheaf
    1.15
    ừ
    1.14
    POSITIVE LOGITS
    el
    1.29
    a
    1.26
    лятор
    0.93
     питания
    0.87
    બર
    0.86
    со
    0.85
    u
    0.84
    ्‍
    0.83
     parar
    0.83
     causa
    0.82
    Activations Density 0.053%

    No Known Activations