© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206896
    Prev
    Next
    INDEX
    Explanations

    boarding school or hostel facilities

    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_20_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
     outwe
    0.46
     Waffen
    0.46
     photore
    0.44
     RAX
    0.44
     பங்க
    0.43
    চল
    0.42
     Ela
    0.41
     복
    0.41
     আঁচ
    0.41
     ലഭ
    0.41
    POSITIVE LOGITS
    Mens
    0.41
    runs
    0.39
    certain
    0.39
    vezet
    0.39
    headless
    0.39
    \
    0.39
    แน
    0.38
    plans
    0.37
    hu
    0.37
    journals
    0.37
    Activations Density 0.000%

    No Known Activations