© 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. 1518
    Prev
    Next
    INDEX
    Explanations

    character count limits

    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_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
    timers
    0.43
    limits
    0.42
     ONE
    0.37
    wärts
    0.37
    ძ
    0.36
     journalists
    0.36
     Madre
    0.36
    >>()
    0.36
    one
    0.35
    Limits
    0.35
    POSITIVE LOGITS
     लोकप्रियता
    0.40
     imprison
    0.38
    豪
    0.38
     Vulcan
    0.37
     popularly
    0.37
    атр
    0.37
     culto
    0.36
    nobyl
    0.36
    陞
    0.36
     shorthand
    0.36
    Activations Density 0.003%

    No Known Activations