© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51396
    Prev
    Next
    INDEX
    Explanations

    definitely ignore

    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_31_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
     комфор
    0.44
     сидя
    0.43
     lounging
    0.43
    Comfort
    0.42
     sofá
    0.40
     शौचालय
    0.39
    盥
    0.39
     sitting
    0.38
    sitting
    0.38
    Sitting
    0.38
    POSITIVE LOGITS
     billing
    0.33
     Retention
    0.32
     witness
    0.31
    ]):
    0.29
     Billing
    0.29
    ಕ್ರ
    0.29
     직선
    0.29
     एसएमएस
    0.29
    ક્રિય
    0.28
    billing
    0.28
    Activations Density 0.015%

    No Known Activations