© 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. 3510
    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
    ே
    2.81
    ра
    2.74
    για
    2.27
    प
    2.25
    ående
    2.23
    غ
    2.17
    紝
    2.11
    и
    2.11
    ج
    2.01
     vý
    1.99
    POSITIVE LOGITS
    ITECTURE
    2.50
    cloth
    2.42
    t
    2.42
    śmy
    2.35
    tica
    2.34
    tte
    2.18
    েনারেল
    2.16
    tonne
    2.12
    tension
    2.07
    اں
    2.06
    Activations Density 0.040%

    No Known Activations