© 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. 2164
    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
    𝚋
    4.13
    ся
    3.28
     molest
    3.18
     наме
    3.17
    ikation
    3.13
    Ꮹ
    3.09
    vertebr
    2.98
    ওলানা
    2.90
    𝚔
    2.85
     cofactor
    2.80
    POSITIVE LOGITS
    я
    4.21
    म
    3.20
    ίδα
    3.01
    鹕
    2.98
    esc
    2.88
    weiß
    2.87
    ます
    2.84
    eating
    2.83
    raspberry
    2.79
    esh
    2.76
    Activations Density 0.059%

    No Known Activations