© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102008
    Prev
    Next
    INDEX
    Explanations

    engagement

    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_14_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
    fangs
    0.51
    ிலி
    0.49
    蓴
    0.49
     Program
    0.48
    峻
    0.48
     Construction
    0.47
    ressing
    0.47
     দিয়
    0.47
    ia
    0.47
     Date
    0.47
    POSITIVE LOGITS
     poem
    0.57
     trove
    0.57
    거
    0.54
    ضای
    0.53
    Przy
    0.51
    вался
    0.51
    וו
    0.50
     ቦታ
    0.50
    ক্ষ
    0.50
     죄
    0.49
    Activations Density 0.007%

    No Known Activations