© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215142
    Prev
    Next
    INDEX
    Explanations

    foreign language feelings

    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_5_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
    ors
    1.21
    able
    1.17
    i
    1.09
    nin
    1.06
     a
    1.02
    lere
    1.02
    ders
    1.01
    د
    1.01
    К
    1.01
    iest
    0.98
    POSITIVE LOGITS
    с
    1.11
    িন
    1.09
    েন
    1.07
    ма
    1.06
    сон
    0.95
    рия
    0.95
    ве
    0.90
    ين
    0.90
    лу
    0.90
    на
    0.89
    Activations Density 0.025%

    No Known Activations