© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16277
    Prev
    Next
    INDEX
    Explanations

    old

    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_15_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
     Buildings
    0.48
     новая
    0.47
     Ni
    0.46
    freie
    0.45
    was
    0.44
     Hamilton
    0.44
     была
    0.42
     は
    0.41
    рана
    0.41
     Henry
    0.41
    POSITIVE LOGITS
     aise
    0.47
    ชีพ
    0.47
     mathsize
    0.47
    缙
    0.47
     بغیر
    0.47
     saddhim
    0.46
    Pacific
    0.45
     mă
    0.45
    DCTask
    0.44
    zelfde
    0.44
    Activations Density 0.006%

    No Known Activations