© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118831
    Prev
    Next
    INDEX
    Explanations

    find a compatible

    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_27_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
     aisles
    0.39
     Fawcett
    0.38
     festgelegt
    0.38
    朔
    0.38
    स्कृत
    0.37
     infrac
    0.37
     tī
    0.37
     將
    0.36
     Attitudes
    0.36
     სტ
    0.35
    POSITIVE LOGITS
    Christian
    0.50
     worried
    0.48
     empres
    0.42
     importância
    0.38
    trump
    0.38
    担心
    0.38
    谗
    0.38
     Christian
    0.38
    onomia
    0.37
    ﺤ
    0.36
    Activations Density 0.002%

    No Known Activations