© 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. 763
    Prev
    Next
    INDEX
    Explanations

    survey methodology and data collection

    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
     dissipation
    0.37
     резо
    0.37
    filtr
    0.36
    ศี
    0.35
    ヒル
    0.35
     システム
    0.35
    esorios
    0.34
    甘
    0.34
     dator
    0.34
     شنا
    0.34
    POSITIVE LOGITS
     survey
    2.48
     surveys
    2.36
    Survey
    2.34
    survey
    2.28
     Survey
    2.27
     Surveys
    2.17
     surveyed
    2.13
     surveying
    2.06
     SURVEY
    2.06
     surveyors
    1.66
    Activations Density 0.079%

    No Known Activations