© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245664
    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_11_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
     colored
    1.10
    ཿ
    1.08
     skiprows
    1.06
     daya
    1.03
    辣椒
    1.01
     stroked
    1.00
     tanya
    0.98
    unu
    0.98
     liquid
    0.97
    jest
    0.97
    POSITIVE LOGITS
    ت
    1.48
    to
    1.17
    Amid
    1.14
    पोल
    1.10
     lontano
    1.05
    visited
    1.03
    tron
    1.01
    ників
    1.01
    offs
    1.00
     abordagem
    1.00
    Activations Density 0.000%

    No Known Activations