© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27899
    Prev
    Next
    INDEX
    Explanations

    percentage followed by a year

    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_40_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
    igna
    0.42
     గురించి
    0.37
     price
    0.37
    Mozilla
    0.36
    價
    0.36
     Mozilla
    0.36
     цена
    0.35
     九
    0.35
    WriteString
    0.35
     سعر
    0.35
    POSITIVE LOGITS
    त्रेयी
    0.37
    প্রকাশ
    0.36
    elessly
    0.34
     సా
    0.34
     Божи
    0.34
    సా
    0.34
     dissolves
    0.34
    endDate
    0.33
    钦
    0.33
     keen
    0.33
    Activations Density 0.001%

    No Known Activations