© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81263
    Prev
    Next
    INDEX
    Explanations

    multi

    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_53_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
     Cost
    0.36
     Orig
    0.36
    Desc
    0.35
    Philip
    0.35
     ca
    0.35
     বপ
    0.35
    Ҫ
    0.35
    sal
    0.35
     Desc
    0.35
     joh
    0.34
    POSITIVE LOGITS
    FFIC
    0.38
    ٹر
    0.38
    汀
    0.38
     आतंकी
    0.38
    Methoxy
    0.36
     कार्यकर्त्या
    0.36
    ترین
    0.35
    óticos
    0.35
    র্ঘ
    0.35
    aniach
    0.34
    Activations Density 0.003%

    No Known Activations