© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67204
    Prev
    Next
    INDEX
    Explanations

    UI interaction events

    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_46_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
     constancy
    0.43
    wała
    0.43
     pumping
    0.42
     Spa
    0.40
    Ờ
    0.40
     পরি
    0.40
     ricost
    0.38
    䂺
    0.38
    irah
    0.38
    erra
    0.38
    POSITIVE LOGITS
    penup
    0.43
     Raise
    0.40
     ezingu
    0.39
    Raise
    0.37
    Raising
    0.37
    Sé
    0.36
     raises
    0.36
     xuống
    0.35
     messagebox
    0.35
     документів
    0.35
    Activations Density 0.002%

    No Known Activations