© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152925
    Prev
    Next
    INDEX
    Explanations

    sunscreen or repellent

    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
    매
    0.42
     adherents
    0.37
    Numerous
    0.35
     Gründe
    0.34
     யா
    0.34
    সাধারণ
    0.33
    ✝
    0.33
    Pittsburgh
    0.33
    Fragment
    0.33
     تَ
    0.33
    POSITIVE LOGITS
    zco
    0.41
    órz
    0.39
    номи
    0.37
     sectors
    0.37
    zte
    0.37
    oreal
    0.37
    iencia
    0.37
     globalisation
    0.37
    conex
    0.36
    iti
    0.36
    Activations Density 0.001%

    No Known Activations