© 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. 246104
    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
     unambiguously
    1.48
    Сегодня
    1.30
    ⺆
    1.28
    glycer
    1.26
     padr
    1.25
    িস
    1.22
     ({\
    1.22
     eclips
    1.21
     regenv
    1.20
     defensively
    1.20
    POSITIVE LOGITS
     Від
    1.03
     banca
    1.01
    ement
    1.01
    ံ့
    1.00
     clubhouse
    0.99
    neo
    0.97
    짬
    0.96
    ende
    0.95
     Purpose
    0.94
     Semester
    0.93
    Activations Density 0.000%

    No Known Activations