© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120513
    Prev
    Next
    INDEX
    Explanations

    phone numbers and contact codes

    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_27_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
    籤
    0.30
    getVisibility
    0.30
    gulpfile
    0.30
     vocal
    0.30
     blogger
    0.30
     करीब
    0.29
     خاصة
    0.29
     rabbi
    0.29
    晦
    0.29
    ziała
    0.29
    POSITIVE LOGITS
     secretion
    0.35
    フリー
    0.32
    無料
    0.31
     無料
    0.30
    Rew
    0.30
     તમારી
    0.29
    מת
    0.29
     protons
    0.28
     dried
    0.28
    Laboratory
    0.28
    Activations Density 0.001%

    No Known Activations