© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51239
    Prev
    Next
    INDEX
    Explanations

    It gets

    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_31_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
    ival
    0.37
    лік
    0.37
     keny
    0.37
    IDAY
    0.36
    itto
    0.34
     통한
    0.34
    ='$
    0.34
    尘
    0.34
    IVAL
    0.34
     पर्
    0.33
    POSITIVE LOGITS
    repetitions
    0.41
    chop
    0.38
     रनों
    0.38
    ┛
    0.38
     repetitions
    0.38
    azawa
    0.37
     iterations
    0.36
     burn
    0.36
     borders
    0.35
    aları
    0.35
    Activations Density 0.006%

    No Known Activations