© 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. 200485
    Prev
    Next
    INDEX
    Explanations

    created successfully

    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
    டப்பட்டது
    0.46
    שהו
    0.43
    uyor
    0.42
    ٪
    0.41
    స్తున్నారు
    0.41
    放題
    0.40
     potranno
    0.40
     যাচ্ছে
    0.40
    aphore
    0.40
     येतात
    0.40
    POSITIVE LOGITS
     deton
    0.38
     गोविंद
    0.38
     celsius
    0.38
    वाह
    0.37
     Rosetta
    0.37
     oun
    0.36
     rf
    0.36
     polo
    0.35
    㼛
    0.35
     reconnect
    0.35
    Activations Density 0.005%

    No Known Activations