© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159357
    Prev
    Next
    INDEX
    Explanations

    แอปพลิเคชัน

    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_2_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
    ных
    1.60
    n
    1.47
    می
    1.30
    inę
    1.30
    ین
    1.29
    nál
    1.24
    اک
    1.19
    مان
    1.19
    리티
    1.17
    ação
    1.15
    POSITIVE LOGITS
     (
    1.40
     -
    1.27
    1.26
     =
    1.24
     in
    1.23
     of
    1.22
    \
    1.21
     )
    1.18
     }
    1.11
     \
    1.10
    Activations Density 0.000%

    No Known Activations