© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206656
    Prev
    Next
    INDEX
    Explanations

    programming concepts

    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_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
    higher
    0.44
     #(
    0.43
    রূপ
    0.41
    #,
    0.41
    started
    0.40
    Higher
    0.39
    almost
    0.38
    pretty
    0.38
    ]')
    0.37
    ]*(
    0.37
    POSITIVE LOGITS
     if
    0.47
     debugger
    0.42
     Assertion
    0.42
     Assert
    0.41
     puts
    0.40
     React
    0.40
     AngularJS
    0.40
     Elasticsearch
    0.39
     ActiveRecord
    0.38
     HBase
    0.38
    Activations Density 0.002%

    No Known Activations