© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13631
    Prev
    Next
    INDEX
    Explanations

    programming data types

    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_13_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
     attacking
    0.53
     Toys
    0.51
    फेक्ट
    0.49
    捣
    0.48
     eating
    0.47
    ıldı
    0.47
    ífico
    0.46
     disagree
    0.46
    ogyakarta
    0.45
    रेखा
    0.45
    POSITIVE LOGITS
     sealer
    0.50
    >∈</
    0.48
    තාව
    0.46
    *;
    0.45
     harbours
    0.45
     prover
    0.44
     consents
    0.44
    *
    0.44
     givenChar
    0.44
    ◦
    0.44
    Activations Density 0.099%

    No Known Activations