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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177454
    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_24_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
    ↵
    0.54
    Pod
    0.50
     Ally
    0.48
     amplitudes
    0.47
    焙
    0.47
     επί
    0.46
    Под
    0.46
     Ricardo
    0.45
    ძ
    0.45
     Riccardo
    0.45
    POSITIVE LOGITS
    雾
    0.46
    詄
    0.44
    سون
    0.44
    名叫
    0.43
     జరిగ
    0.43
    omor
    0.42
     vuoden
    0.42
    مارسة
    0.41
    浃
    0.41
    omorph
    0.41
    Activations Density 0.000%

    No Known Activations