© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75471
    Prev
    Next
    INDEX
    Explanations

    sunscreen, UV rays, skin protection

    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_31_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
     Sunlight
    0.57
     sunlight
    0.55
     солне
    0.52
     햇
    0.48
     sunshine
    0.45
     photosynthetic
    0.40
    阳光
    0.40
     photore
    0.40
     solar
    0.39
     చీ
    0.39
    POSITIVE LOGITS
     mechanically
    0.46
    pint
    0.43
    rifle
    0.42
    멕
    0.39
     Oz
    0.38
     terme
    0.37
    Oz
    0.37
     কই
    0.37
    Normal
    0.36
     kanal
    0.36
    Activations Density 0.014%

    No Known Activations