© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146435
    Prev
    Next
    INDEX
    Explanations

    Ok, sum, num, println

    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_18_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
    ermost
    0.50
    ुट
    0.46
    ुत
    0.46
    签
    0.45
     specification
    0.45
     specifications
    0.44
    ύν
    0.44
     misalnya
    0.44
    \",
    0.44
     स्थान
    0.43
    POSITIVE LOGITS
    s
    0.52
     Hug
    0.52
     Recurs
    0.52
     Habsburg
    0.50
     행복
    0.50
    ])),
    0.49
     Cé
    0.49
     Galaxies
    0.48
     HCO
    0.48
    리를
    0.48
    Activations Density 0.000%

    No Known Activations