© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260703
    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
    ôn
    0.51
    ì
    0.50
    ী
    0.47
    yc
    0.46
    icar
    0.45
    ı
    0.45
    ๒
    0.44
    orn
    0.44
     across
    0.44
    ąg
    0.42
    POSITIVE LOGITS
    کا
    0.47
     proteínas
    0.46
    🦾
    0.46
     मांस
    0.45
     menacing
    0.45
     masker
    0.45
     humiliating
    0.44
     limiting
    0.43
     incriminating
    0.43
     правило
    0.42
    Activations Density 0.000%

    No Known Activations