© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261054
    Prev
    Next
    INDEX
    Explanations

    rephrase

    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_5_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
    u
    1.28
    on
    1.25
    '
    1.24
    ’
    1.09
    in
    0.97
    疼
    0.92
    ches
    0.91
    tti
    0.88
    ಗೊಂಡ
    0.88
    的时
    0.87
    POSITIVE LOGITS
    ен
    1.38
    ки
    1.20
    ре
    1.18
    ای
    1.16
     impuestos
    1.12
    د
    1.12
    াত
    1.07
     favoritos
    1.07
    ర్
    1.05
    イ
    1.05
    Activations Density 0.000%

    No Known Activations