© 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. 43784
    Prev
    Next
    INDEX
    Explanations

    rise and fall of Case

    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
     competitiveness
    0.44
    тус
    0.44
    ន៍
    0.43
    ᅳ
    0.42
    ْس
    0.40
    साठी
    0.39
    ンス
    0.39
    ش
    0.39
     ସ
    0.39
     cít
    0.39
    POSITIVE LOGITS
    kable
    0.47
     eventual
    0.38
    permanent
    0.38
    που
    0.37
     история
    0.37
    pointer
    0.37
     eternal
    0.37
    ATI
    0.36
    ido
    0.36
    gli
    0.36
    Activations Density 0.004%

    No Known Activations