© 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
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 37420
    Prev
    Next
    INDEX
    Explanations

    wi or red

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     कोणते
    0.39
     Hogan
    0.38
    ظ
    0.38
    铍
    0.38
     Shrimp
    0.37
    dihydroxy
    0.37
     Halsey
    0.36
    qos
    0.36
     ArrayRef
    0.36
     faz
    0.36
    POSITIVE LOGITS
    wi
    0.79
     red
    0.68
     wi
    0.68
    イ
    0.67
    WI
    0.63
    red
    0.61
    Wi
    0.57
     rod
    0.54
    wia
    0.54
    Red
    0.53
    Activations Density 0.003%

    No Known Activations