© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53410
    Prev
    Next
    INDEX
    Explanations

    visible pores, scars, toes, socks

    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_30_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
     Westbrook
    0.39
     trama
    0.39
     ور
    0.38
    obile
    0.36
    नाम
    0.36
    喬
    0.36
     superhero
    0.36
     appellate
    0.36
     رجسٹ
    0.35
    सलमान
    0.35
    POSITIVE LOGITS
     toen
    0.36
    äten
    0.34
     მიმო
    0.34
    욱
    0.34
     Books
    0.34
     Socks
    0.34
     посу
    0.33
     Toen
    0.33
    τε
    0.33
     Foot
    0.33
    Activations Density 0.033%

    No Known Activations