© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61352
    Prev
    Next
    INDEX
    Explanations

    instructions or corrections

    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_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
     p
    0.64
    ↵
    0.57
    ate
    0.57
     ethical
    0.57
     Coss
    0.56
     medieval
    0.55
     best
    0.54
     station
    0.54
     landscape
    0.54
     activism
    0.54
    POSITIVE LOGITS
     vaisseaux
    0.58
    ίλ
    0.58
     trois
    0.57
    ၃
    0.56
    薩
    0.54
    тено
    0.54
    -$\
    0.52
    teries
    0.52
    testid
    0.51
    hydes
    0.50
    Activations Density 0.030%

    No Known Activations