© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36908
    Prev
    Next
    INDEX
    Explanations

    comments

    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_11_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
    <0x0D>
    0.88
     esterno
    0.69
     עם
    0.68
     malla
    0.66
     düzenlenen
    0.66
    alla
    0.66
     ר
    0.66
     externo
    0.66
     variado
    0.64
     deportivo
    0.61
    POSITIVE LOGITS
    ۰
    0.64
     Kā
    0.61
    ﻠ
    0.58
    𝗟
    0.57
    зи
    0.55
    ﺐ
    0.55
    ᓛ
    0.54
     Mā
    0.54
    ⴽ
    0.54
    Sale
    0.53
    Activations Density 0.000%

    No Known Activations