© 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. 35485
    Prev
    Next
    INDEX
    Explanations

    websites or URLs

    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
    Fl
    0.40
    Gav
    0.40
     พอ
    0.40
    ப்பட்டி
    0.38
    侦
    0.38
    agas
    0.38
    gav
    0.38
    鏝
    0.38
     gav
    0.37
     स्थिरता
    0.37
    POSITIVE LOGITS
    vdots
    0.38
     জিনি
    0.38
    EntryPoint
    0.38
    詳
    0.38
    emia
    0.36
     Turning
    0.36
     HE
    0.35
     alkaloids
    0.35
    ুদের
    0.34
     Sandals
    0.34
    Activations Density 0.065%

    No Known Activations