© 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. 220778
    Prev
    Next
    INDEX
    Explanations

    age descriptions (e.g., 15 year old)

    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
    CHO
    0.30
     내
    0.29
     laboratory
    0.29
     직접
    0.29
     ATO
    0.29
     Laboratory
    0.28
    OCA
    0.28
     sciences
    0.28
     ಪ್ರಯ
    0.28
     fable
    0.28
    POSITIVE LOGITS
    ăpadă
    0.36
    ປ
    0.32
    ភាគ
    0.31
     wearer
    0.31
    ępuje
    0.31
     ngôi
    0.30
    卡的
    0.29
    сал
    0.29
     perioada
    0.29
    uteen
    0.29
    Activations Density 0.005%

    No Known Activations