© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162033
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    \},\
    0.46
    Ⲃ
    0.42
     Inheritance
    0.36
     recort
    0.36
    苅
    0.35
    Contributing
    0.35
     nutzen
    0.35
    クサ
    0.34
    鵰
    0.34
     Beitrag
    0.34
    POSITIVE LOGITS
     antennae
    0.41
    storage
    0.41
     superficie
    0.40
     بوص
    0.38
     stored
    0.37
     डेली
    0.37
    stored
    0.37
    assert
    0.36
     ओम
    0.36
    诚信
    0.35
    Activations Density 0.000%

    No Known Activations