© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166593
    Prev
    Next
    INDEX
    Explanations

    shuffle data

    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_56_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
     sh
    3.03
    sh
    2.05
     Sh
    1.86
     ش
    1.74
    Sh
    1.74
     ш
    1.59
     श
    1.49
     sho
    1.45
     Sho
    1.42
     shunt
    1.41
    POSITIVE LOGITS
     felicit
    0.35
    ่ย
    0.34
    撗
    0.34
    databind
    0.33
    PIRED
    0.32
    毕
    0.32
     khủng
    0.32
     कुर
    0.32
    йы
    0.31
    ঠাকুর
    0.31
    Activations Density 0.010%

    No Known Activations