© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16257
    Prev
    Next
    INDEX
    Explanations

    severing or breaking connections

    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
    㤓
    0.58
     wurde
    0.53
     শীঘ্রই
    0.52
     '".$
    0.52
    ’.”
    0.52
    ized
    0.51
    лийн
    0.51
    '.
    0.50
    '];
    0.50
    }}=-\
    0.50
    POSITIVE LOGITS
    Зак
    0.55
    broken
    0.54
    斷
    0.54
     bridges
    0.53
    स्तानी
    0.53
    اہے
    0.52
    셉
    0.52
     Renault
    0.52
    bridges
    0.51
    breaks
    0.51
    Activations Density 0.026%

    No Known Activations