© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175816
    Prev
    Next
    INDEX
    Explanations

    Company names

    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_50_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
    MIC
    0.41
    𒈾
    0.39
     میز
    0.38
     بهره
    0.38
     মিয়া
    0.38
    ittee
    0.37
     الصوت
    0.37
     MIA
    0.37
     प्रभारी
    0.37
     fortified
    0.37
    POSITIVE LOGITS
     Gru
    0.41
     Sunshine
    0.41
    Gruß
    0.39
    Gru
    0.38
     Partial
    0.38
     Ко
    0.38
    齑
    0.37
     Sund
    0.37
     Jérôme
    0.36
    紅茶
    0.36
    Activations Density 0.017%

    No Known Activations