© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228384
    Prev
    Next
    INDEX
    Explanations

    at

    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_57_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
    ally
    0.48
    ing
    0.47
    e
    0.45
    ean
    0.42
    er
    0.39
    ed
    0.39
    ING
    0.38
     nah
    0.38
    ly
    0.37
    ственную
    0.37
    POSITIVE LOGITS
    koľ
    0.39
    ypso
    0.39
    pekt
    0.38
    ້ນ
    0.38
    訶
    0.37
    ⿷
    0.37
    बिर
    0.36
     voy
    0.35
     نهايه
    0.34
    uccio
    0.34
    Activations Density 0.001%

    No Known Activations