© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50455
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    裁剪
    0.42
     instill
    0.37
     ordained
    0.37
    ⑧
    0.35
     eighth
    0.35
    નિ
    0.32
    থি
    0.32
     monomial
    0.32
    evole
    0.32
    Ⅷ
    0.32
    POSITIVE LOGITS
     बुखार
    0.36
     दरम्यान
    0.36
     BLOG
    0.34
     ach
    0.34
    IVATE
    0.33
     consecuencias
    0.33
    വ്ര
    0.33
     DEPARTMENT
    0.33
    वर्ती
    0.33
     interview
    0.32
    Activations Density 0.000%

    No Known Activations