© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33987
    Prev
    Next
    INDEX
    Explanations

    German factual texts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     heft
    0.99
     hæ
    0.94
     Hef
    0.92
     hä
    0.76
     Heft
    0.76
    he
    0.70
     HE
    0.68
    ヘ
    0.68
     hé
    0.65
    HE
    0.64
    POSITIVE LOGITS
    gut
    0.49
    Gut
    0.44
     Gut
    0.43
     Гер
    0.38
     гер
    0.37
     இ
    0.36
     الش
    0.36
     sugar
    0.36
     perjud
    0.36
    стом
    0.35
    Activations Density 0.000%

    No Known Activations