© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119846
    Prev
    Next
    INDEX
    Explanations

    to provide safe and ethical

    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_27_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
     encomendas
    0.31
     Normally
    0.29
    芊
    0.29
    $/
    0.29
     crack
    0.28
    crack
    0.28
     Crack
    0.27
     responsabil
    0.26
     تجربه
    0.26
     investigador
    0.26
    POSITIVE LOGITS
    跻
    0.30
    더
    0.27
     основные
    0.26
    杰
    0.26
     주요
    0.26
    antal
    0.26
    十二
    0.26
    рные
    0.25
     passag
    0.25
     छठी
    0.25
    Activations Density 0.013%

    No Known Activations