© 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. 79591
    Prev
    Next
    INDEX
    Explanations

    logging configuration

    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
     reverted
    0.36
     reverting
    0.35
     sā
    0.34
     reverts
    0.34
    ቧ
    0.33
     log
    0.33
     भूमि
    0.33
     tjän
    0.33
     diya
    0.32
    εια
    0.32
    POSITIVE LOGITS
     German
    0.34
    Angular
    0.33
     Anteil
    0.33
     reuse
    0.33
    电压
    0.32
     г
    0.31
     বিছ
    0.31
    pubs
    0.31
     Gett
    0.31
     Reuse
    0.31
    Activations Density 0.002%

    No Known Activations