© 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. 141136
    Prev
    Next
    INDEX
    Explanations

    codes and abbreviations

    np_max-act-logits · gemini-2.5-flash-lite
    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
    ampionship
    0.38
     MODULE
    0.38
     Resolved
    0.37
     Segment
    0.37
    დე
    0.37
     வளர்
    0.36
     #"
    0.36
     DOC
    0.36
    ❉
    0.35
     Evaluations
    0.35
    POSITIVE LOGITS
    förm
    0.39
     aproximadamente
    0.36
     finely
    0.36
    GetOffset
    0.35
    售
    0.35
     fortemente
    0.35
     ger
    0.34
     positively
    0.34
     completamente
    0.34
    ('$(
    0.34
    Activations Density 0.001%

    No Known Activations