© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44033
    Prev
    Next
    INDEX
    Explanations

    Wikipedia neutrality and notability guidelines

    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_13_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
     Ment
    0.35
    ♲
    0.35
    Ment
    0.34
     lysosomes
    0.34
    Temperatura
    0.33
     estatura
    0.33
     mentoring
    0.33
    брита
    0.32
     Rembrandt
    0.32
     internazionali
    0.32
    POSITIVE LOGITS
    ﺪ
    0.35
     needless
    0.32
    に見
    0.31
     hizmet
    0.30
    ية
    0.30
     should
    0.29
     years
    0.29
     liệt
    0.29
    ה
    0.29
    ᆯ
    0.28
    Activations Density 0.001%

    No Known Activations