© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245392
    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
    .>
    1.43
     positivity
    1.32
    țile
    1.32
     albeit
    1.31
     donuts
    1.30
     oftent
    1.26
    𝘧
    1.24
     doughnuts
    1.24
     dignit
    1.21
    ená
    1.21
    POSITIVE LOGITS
     else
    1.12
    c
    1.06
     bawah
    1.04
    ள்ள
    1.04
    k
    1.01
    날
    0.98
    else
    0.95
    UAE
    0.94
    вання
    0.93
    sen
    0.92
    Activations Density 0.000%

    No Known Activations