© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208910
    Prev
    Next
    INDEX
    Explanations

    software download links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     serão
    0.16
    mathscr
    0.16
    нется
    0.16
    Abraham
    0.15
    Acknowledg
    0.15
    ('-
    0.15
     vendido
    0.15
    Wesley
    0.15
    gomery
    0.14
     خواهند
    0.14
    POSITIVE LOGITS
     Pharma
    0.17
    ⅓
    0.17
    /
    0.17
     PVC
    0.16
     blinking
    0.16
     “
    0.16
     Pix
    0.16
     Ult
    0.16
    最具
    0.16
    ЕР
    0.15
    Activations Density 0.000%

    No Known Activations