© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209028
    Prev
    Next
    INDEX
    Explanations

    meeting of the

    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_19_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
     Крем
    0.42
    驷
    0.41
     няколко
    0.40
     दर्
    0.39
     వార
    0.39
     क्र
    0.39
     regrowth
    0.39
     която
    0.39
    दो
    0.38
     vigorous
    0.38
    POSITIVE LOGITS
     باہر
    0.48
    AI
    0.44
    外部
    0.44
    SCE
    0.41
    ਿ
    0.40
    相位
    0.39
    ব্লিউ
    0.39
     وابسته
    0.39
    พื้นที่
    0.39
    itors
    0.39
    Activations Density 0.000%

    No Known Activations