© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260829
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
    ayment
    0.46
    🫰
    0.45
     merit
    0.44
     tomography
    0.41
     vib
    0.40
     citizenship
    0.40
    oción
    0.40
     discounting
    0.40
     hydrolysis
    0.39
     fermentation
    0.39
    POSITIVE LOGITS
    ज
    0.49
     Bahkan
    0.46
     Muchos
    0.46
    ט
    0.44
    ključ
    0.43
     Shoulder
    0.43
    بے
    0.42
    나는
    0.42
     Rhythm
    0.42
     रिज
    0.42
    Activations Density 0.000%

    No Known Activations