© 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. 15766
    Prev
    Next
    INDEX
    Explanations

    geographical locations and conditions

    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
    Grade
    0.61
     grade
    0.57
    low
    0.55
    grade
    0.53
    Low
    0.51
     Grade
    0.50
     GRADE
    0.47
    低
    0.47
     low
    0.46
    LOW
    0.46
    POSITIVE LOGITS
     Reliability
    0.52
     reliability
    0.51
     reliable
    0.45
    Reli
    0.41
    reliability
    0.41
    邛
    0.40
     trustworthy
    0.39
     unut
    0.39
     unreliable
    0.39
     Reliable
    0.38
    Activations Density 0.085%

    No Known Activations