© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 4395
    Prev
    Next
    INDEX
    Explanations

    media

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     bì
    0.36
    orative
    0.35
    arta
    0.35
     ro
    0.35
    ỳnh
    0.35
    orsun
    0.35
     형
    0.34
    urbation
    0.34
     interesting
    0.34
     အ
    0.34
    POSITIVE LOGITS
     media
    3.16
    media
    2.83
     Media
    2.83
    Media
    2.75
     MEDIA
    2.66
     मीडिया
    2.55
    媒体
    2.55
    メディア
    2.52
    媒體
    2.48
    MEDIA
    2.47
    Activations Density 0.130%

    No Known Activations