© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68005
    Prev
    Next
    INDEX
    Explanations

    eager to contribute

    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_51_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
    ృతి
    0.46
    тити
    0.44
    리티
    0.44
    ৃতি
    0.43
    緹
    0.43
     monies
    0.41
    ˆ‚
    0.41
     tempHeader
    0.40
    提
    0.39
    菻
    0.38
    POSITIVE LOGITS
    চ্ছে
    0.51
    Id
    0.42
    сня
    0.41
    ચ્છ
    0.39
    IDAE
    0.39
    eds
    0.39
    ICC
    0.39
    idae
    0.39
    udet
    0.39
     icc
    0.39
    Activations Density 0.000%

    No Known Activations