© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129423
    Prev
    Next
    INDEX
    Explanations

    numbers followed by days or years

    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_1_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
    EL
    1.04
    的
    0.96
    ED
    0.93
     set
    0.91
     về
    0.88
     ligne
    0.88
     في
    0.87
     gelegen
    0.86
     gewährleisten
    0.86
    де
    0.85
    POSITIVE LOGITS
    א
    1.45
    י
    1.31
    ie
    1.09
    ੀ
    1.04
    но
    1.01
    i
    1.00
    و
    1.00
    ד
    0.98
    iet
    0.96
    ंद
    0.94
    Activations Density 0.030%

    No Known Activations