© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124796
    Prev
    Next
    INDEX
    Explanations

    simple

    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_37_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
    下图
    0.42
     repl
    0.40
     servants
    0.37
    揩
    0.37
     كيفية
    0.36
     affirmation
    0.36
     formul
    0.36
     participation
    0.35
     driver
    0.35
     hic
    0.35
    POSITIVE LOGITS
     extremely
    0.47
     крайне
    0.46
     extremadamente
    0.43
    非常に
    0.40
     очень
    0.39
    დეს
    0.39
    स्टेंस
    0.39
    燊
    0.39
    態度
    0.39
     estremamente
    0.39
    Activations Density 0.018%

    No Known Activations