© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5190
    Prev
    Next
    INDEX
    Explanations

    dates, especially today's date

    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_39_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
    <0xE2>
    0.29
     GLA
    0.27
    ridas
    0.27
    आत
    0.26
    ούμε
    0.26
    WER
    0.26
    ⠄
    0.26
    åd
    0.25
    gano
    0.25
    瘘
    0.25
    POSITIVE LOGITS
    主办
    0.32
    𝗆
    0.30
    主催
    0.30
     dom
    0.29
     ഇഷ്ട
    0.29
     niezb
    0.29
     postice
    0.29
     Prothorax
    0.29
    ക്തി
    0.29
     routing
    0.28
    Activations Density 0.026%

    No Known Activations