© 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
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52039
    Prev
    Next
    INDEX
    Explanations

    grammatical components

    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_55_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
    ต้
    0.40
    уз
    0.40
    ☮
    0.38
    subNav
    0.38
    やって
    0.37
    やった
    0.37
    ᡠ
    0.36
     olup
    0.36
    สุ
    0.35
    }<
    0.35
    POSITIVE LOGITS
     det
    0.45
     dét
    0.42
    MDET
    0.41
     Det
    0.39
    det
    0.39
     DET
    0.37
     ഫാ
    0.37
     say
    0.37
    ళ
    0.37
     pron
    0.37
    Activations Density 0.000%

    No Known Activations