© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34788
    Prev
    Next
    INDEX
    Explanations

    voice commands

    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
    ्मी
    0.40
     generalize
    0.40
     exchanging
    0.40
     kneel
    0.39
    䅐
    0.39
    encial
    0.37
    })(\
    0.37
     আর্ত
    0.37
     سکے۔
    0.37
    栝
    0.37
    POSITIVE LOGITS
    歌曲
    0.37
     કપ
    0.36
     calendário
    0.36
    Establish
    0.35
    订
    0.35
     calendar
    0.35
     বাল
    0.35
    oge
    0.35
    VPN
    0.35
     JSTOR
    0.35
    Activations Density 0.058%

    No Known Activations