© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85627
    Prev
    Next
    INDEX
    Explanations

    vowels including 'u'

    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_18_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
     पारिवारिक
    0.56
     flexion
    0.55
    स्तिष्क
    0.48
    ])$.
    0.48
    }$;
    0.48
     lesion
    0.48
     प्रतिबंध
    0.48
     Polym
    0.48
     atheros
    0.47
     ар
    0.47
    POSITIVE LOGITS
    NASA
    0.56
     Nagata
    0.53
    has
    0.51
    WT
    0.49
    had
    0.49
     has
    0.48
     جهانی
    0.48
     had
    0.47
    ➁
    0.46
    دارة
    0.45
    Activations Density 0.003%

    No Known Activations