© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259813
    Prev
    Next
    INDEX
    Explanations

    security features and considerations

    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_22_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
     bounty
    0.45
     ወ
    0.41
     prizes
    0.41
     prairie
    0.40
     согла
    0.39
     Bounty
    0.39
     pale
    0.38
     strollers
    0.38
    ige
    0.38
    盃
    0.37
    POSITIVE LOGITS
    然后再
    0.47
     localizada
    0.42
     Eigent
    0.40
     StringBuilder
    0.40
    水道
    0.39
     শারীরিক
    0.39
     встроен
    0.39
     الفيزياء
    0.38
    ToListAsync
    0.38
     ambiental
    0.38
    Activations Density 0.001%

    No Known Activations