© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23772
    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_56_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
    דיה
    0.42
    "--
    0.42
    rimps
    0.41
     ecol
    0.40
    pro
    0.40
     amps
    0.39
    Pro
    0.39
    [][
    0.39
     प्रेस
    0.38
    POSITIVE LOGITS
     artikkel
    0.45
     artik
    0.39
     article
    0.39
     artículo
    0.39
     industriale
    0.39
     artikel
    0.39
     статью
    0.39
     articolo
    0.38
     glorified
    0.38
     livré
    0.38
    Activations Density 0.000%

    No Known Activations