© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65751
    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_46_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
    ປີ
    0.37
     Compound
    0.36
     Comment
    0.36
     tros
    0.35
    房
    0.35
     Cou
    0.35
     microw
    0.34
     perce
    0.34
     Perception
    0.34
     fair
    0.34
    POSITIVE LOGITS
    ulated
    0.52
    transmitted
    0.45
    relative
    0.41
    ributing
    0.41
    ⱨ
    0.41
    bsch
    0.40
    相対
    0.40
    ified
    0.39
    ização
    0.38
    Holmes
    0.38
    Activations Density 0.000%

    No Known Activations