© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61359
    Prev
    Next
    INDEX
    Explanations

    culturally significant

    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_11_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
    ᴋ
    0.57
     Loops
    0.55
     Boats
    0.52
    nels
    0.51
     Pools
    0.51
     प्
    0.50
     Equals
    0.50
     Honduras
    0.50
     direto
    0.50
    ешься
    0.50
    POSITIVE LOGITS
    </
    0.73
    י
    0.59
    ">
    0.57
    ו
    0.56
    מצא
    0.55
    িও
    0.55
     όχι
    0.53
     نتیجه
    0.52
    廛
    0.52
    ုန်
    0.51
    Activations Density 0.004%

    No Known Activations