© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259312
    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_10_width_262k_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
     adhesion
    1.20
    ⠀⠀
    1.10
     urged
    1.09
     agrega
    1.07
    ointed
    1.03
     berths
    1.02
     warfare
    1.02
     insanity
    1.01
     overcoming
    1.00
     chills
    1.00
    POSITIVE LOGITS
     decât
    1.18
    𝙜
    1.17
    min
    1.13
    к
    1.12
    draggable
    1.09
    ga
    1.08
     Picasso
    1.08
    𝙝
    1.07
    ষ্ট্র
    1.07
     riten
    1.06
    Activations Density 0.000%

    No Known Activations