© 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. 1973
    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
    у
    1.99
    Чтобы
    1.91
    ertura
    1.77
     mož
    1.75
    а
    1.72
    ال
    1.65
    Atual
    1.65
    lığ
    1.62
     bevor
    1.59
    ർ
    1.58
    POSITIVE LOGITS
    as
    2.13
    ्स
    2.01
    aschen
    2.00
    𝘂
    1.96
    ی
    1.92
    いない
    1.85
    concern
    1.84
    𝘀
    1.82
    i
    1.82
    graduate
    1.80
    Activations Density 0.038%

    No Known Activations