© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4278
    Prev
    Next
    INDEX
    Explanations

    inferring types

    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
     strCmd
    0.54
     স্ট্যান্ডার্ড
    0.44
    काब
    0.41
    რა
    0.41
    岑
    0.39
    デル
    0.39
    ֆ
    0.39
    倜
    0.38
    ಶ್ರೀ
    0.38
     전기
    0.37
    POSITIVE LOGITS
     inferred
    0.66
     infer
    0.65
    Infer
    0.59
     inference
    0.59
     deduced
    0.55
     Inference
    0.53
     Infer
    0.51
    inference
    0.51
     inferences
    0.47
    infer
    0.47
    Activations Density 0.002%

    No Known Activations