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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260485
    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
     ï
    1.06
    weets
    1.04
    ോഷ്യ
    1.01
    --’
    0.99
     breathe
    0.99
    적이
    0.98
    적으로
    0.97
    mLogin
    0.96
    <\
    0.96
     partake
    0.95
    POSITIVE LOGITS
    ts
    1.05
    z
    1.04
     lacked
    0.95
    acido
    0.93
     asymmetry
    0.93
    tsy
    0.91
    ⿸
    0.91
    ذج
    0.91
    对称
    0.90
    tmux
    0.90
    Activations Density 0.000%

    No Known Activations