© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174707
    Prev
    Next
    INDEX
    Explanations

    Families

    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
    卷
    0.47
     Leland
    0.47
     Keith
    0.45
     Carlton
    0.44
     말미
    0.43
    िंग
    0.43
    ፏ
    0.42
     початку
    0.42
     त्यांचे
    0.41
    笛
    0.41
    POSITIVE LOGITS
     bitterly
    0.50
    fers
    0.47
    Ex
    0.44
    ro
    0.43
    even
    0.43
    áns
    0.42
     redox
    0.42
    regex
    0.42
    gate
    0.42
    EP
    0.41
    Activations Density 0.001%

    No Known Activations