© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229719
    Prev
    Next
    INDEX
    Explanations

    single source of truth

    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_6_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
    ↵
    1.26
     ד
    1.05
     can
    0.97
     הב
    0.96
     metastatic
    0.94
    .</
    0.93
    1
    0.92
     fisherman
    0.89
    4
    0.87
     מר
    0.85
    POSITIVE LOGITS
    ur
    1.17
    xious
    1.08
    ag
    1.07
    j
    1.01
    é
    1.00
    дцать
    0.98
    digits
    0.98
    rieben
    0.97
     fouls
    0.97
    rials
    0.96
    Activations Density 0.001%

    No Known Activations