© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90699
    Prev
    Next
    INDEX
    Explanations

    notify

    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_11_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
     綿
    0.64
    ام
    0.63
     okres
    0.60
    場所に
    0.59
     despre
    0.59
    akkhati
    0.59
     zuten
    0.57
     kuhusu
    0.57
     zucchero
    0.56
     жана
    0.55
    POSITIVE LOGITS
    н
    0.66
    kiem
    0.65
     CFO
    0.63
    ki
    0.62
    Editorial
    0.61
    ko
    0.58
     IQ
    0.58
    Abroad
    0.57
    Adapt
    0.57
    Essentials
    0.57
    Activations Density 0.001%

    No Known Activations