© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12233
    Prev
    Next
    INDEX
    Explanations

    questions about what is

    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_13_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
    )$
    0.65
    )।
    0.57
    )-\
    0.57
    glightbox
    0.54
     আমদানি
    0.54
     ဒါ
    0.54
    ।)
    0.54
    )\
    0.54
    )</
    0.54
    countries
    0.54
    POSITIVE LOGITS
     altercation
    0.59
     spore
    0.54
    and
    0.52
     resemblance
    0.50
     consolation
    0.50
    特定
    0.50
     personalities
    0.49
     reluctance
    0.48
     calend
    0.48
     hostage
    0.48
    Activations Density 0.000%

    No Known Activations