© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18451
    Prev
    Next
    INDEX
    Explanations

    was

    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_15_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
    ใน
    0.13
     RNN
    0.13
    ке
    0.13
    k
    0.12
    ו
    0.12
     religion
    0.12
    ло
    0.11
    ک
    0.11
     console
    0.11
     ionization
    0.11
    POSITIVE LOGITS
     અથવા
    0.14
     அல்லது
    0.14
     budete
    0.14
     oppure
    0.13
     ব্রাজ
    0.13
     ಅಥವಾ
    0.13
     లేదా
    0.13
    或者
    0.13
     හෝ
    0.12
     或者
    0.12
    Activations Density 0.352%

    No Known Activations