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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29686
    Prev
    Next
    INDEX
    Explanations

    black

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     a
    0.34
     an
    0.34
     ā
    0.33
     ħ
    0.33
     ఉండ
    0.32
    
    0.32
     it
    0.31
     ū
    0.30
    🐚
    0.30
     atmósfera
    0.29
    POSITIVE LOGITS
    at
    0.46
    for
    0.37
    <0x80>
    0.33
    т
    0.30
    ch
    0.30
    i
    0.30
     stara
    0.29
    n
    0.29
    0
    0.29
    Qualified
    0.28
    Activations Density 0.010%

    No Known Activations