© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134008
    Prev
    Next
    INDEX
    Explanations

    Which of the following statements

    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_37_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
     اوس
    0.41
     laser
    0.39
    াধ
    0.38
     waves
    0.38
     بو
    0.38
     hou
    0.38
     دام
    0.37
    🅔
    0.37
     चल
    0.36
     láser
    0.36
    POSITIVE LOGITS
    ges
    0.42
    jel
    0.37
    臼
    0.36
    真正
    0.36
    steen
    0.36
     پرست
    0.35
     dadurch
    0.35
    ृता
    0.34
     എന്നു
    0.34
    ඨ
    0.34
    Activations Density 0.001%

    No Known Activations