© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144632
    Prev
    Next
    INDEX
    Explanations

    uncanny valley

    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_0_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
    1.66
     de
    1.21
    getCql
    1.20
    এম
    1.18
     উঠিয়া
    1.18
     တို့
    1.17
    ă
    1.16
    كة
    1.16
    tLogRow
    1.16
     করিয়৷
    1.14
    POSITIVE LOGITS
    י
    2.77
    an
    2.30
    i
    2.30
    ي
    2.23
    at
    1.95
    ا
    1.91
    ে
    1.88
    ב
    1.87
    د
    1.85
    ו
    1.82
    Activations Density 0.000%

    No Known Activations