© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34409
    Prev
    Next
    INDEX
    Explanations

    tuition, college, financial aid, accredited

    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
    緣
    0.46
     MSE
    0.42
     officer
    0.42
     flakes
    0.41
    хоро
    0.39
     Miz
    0.38
     Schne
    0.37
     legislative
    0.37
     OPT
    0.37
     মিজান
    0.37
    POSITIVE LOGITS
     donors
    0.50
    聖
    0.49
     Saints
    0.46
     saints
    0.45
    saint
    0.43
    圣
    0.42
     thánh
    0.42
     saint
    0.41
     dyn
    0.41
     religiosas
    0.40
    Activations Density 0.011%

    No Known Activations