© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151599
    Prev
    Next
    INDEX
    Explanations

    cream butter and sugars mixture

    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_23_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
    editors
    0.47
    ה
    0.45
    也會
    0.42
     katana
    0.42
    interpreter
    0.41
     occuring
    0.41
    ه
    0.41
     polyd
    0.40
    cherche
    0.39
    שׁ
    0.38
    POSITIVE LOGITS
     Contin
    0.43
     {[
    0.43
    माइ
    0.42
     outbound
    0.41
    ımız
    0.41
     Circus
    0.41
    ंबर
    0.41
     comunes
    0.40
     Mason
    0.40
    larınız
    0.39
    Activations Density 0.000%

    No Known Activations