© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243828
    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_40_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
    뗑
    0.49
    isr
    0.42
    itin
    0.41
    ulling
    0.39
     hypothesis
    0.39
     cero
    0.39
     ume
    0.38
    ritten
    0.37
    कक्ष
    0.37
     अटेम्प्ट
    0.37
    POSITIVE LOGITS
     Charakter
    0.41
     Character
    0.40
    Character
    0.39
     CHARACTER
    0.38
    Crystal
    0.38
     源
    0.38
    CHP
    0.37
    ┣
    0.36
     Grund
    0.36
    GetObject
    0.35
    Activations Density 0.000%

    No Known Activations