© 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. 205730
    Prev
    Next
    INDEX
    Explanations

    Not

    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
     그냥
    0.40
    殆
    0.39
    幾乎
    0.37
     prácticamente
    0.37
     diferente
    0.36
    縫
    0.36
     모두
    0.36
    င်း
    0.36
     !=
    0.34
     插
    0.34
    POSITIVE LOGITS
    ബി
    0.41
    জিওথেরাপি
    0.38
    বিশেষ
    0.38
     बर्फ
    0.37
    IVACON
    0.36
     ব্যাপক
    0.35
     maxHeight
    0.35
     θ
    0.34
     ステン
    0.34
     உண்டா
    0.34
    Activations Density 0.002%

    No Known Activations