© 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. 3330
    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
    м
    3.12
    er
    2.66
    е
    2.59
    ة
    2.50
    й
    2.41
    ed
    2.33
    л
    2.28
    ა
    2.12
    ം
    2.00
    age
    1.98
    POSITIVE LOGITS
    wann
    2.20
    cule
    2.20
    gli
    2.18
    YM
    2.08
    damaged
    2.07
    ఒ
    2.07
    tare
    2.04
    Το
    2.04
    xon
    2.04
    Bere
    1.99
    Activations Density 0.243%

    No Known Activations