© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214390
    Prev
    Next
    INDEX
    Explanations

    German 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
    :
    0.39
    ;
    0.38
    okit
    0.38
     laid
    0.36
    InnoDB
    0.35
    ilt
    0.35
     tied
    0.35
     Branco
    0.35
     bent
    0.35
     उर्फ
    0.35
    POSITIVE LOGITS
    poetrylovers
    0.42
    بری
    0.38
    거
    0.38
    तीर्ण
    0.37
     sooner
    0.37
     чрезвы
    0.37
    对了
    0.37
     지난해
    0.36
    trä
    0.36
    dif
    0.36
    Activations Density 0.003%

    No Known Activations