© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132514
    Prev
    Next
    INDEX
    Explanations

    chibi style characters

    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_6_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
    J
    0.90
    ჯ
    0.87
     smlou
    0.86
    on
    0.83
    乆
    0.83
    ۹
    0.81
    방법
    0.80
    I
    0.79
     I
    0.79
    with
    0.78
    POSITIVE LOGITS
    0
    1.24
    د
    1.09
    da
    1.05
    ne
    1.02
    d
    1.01
     or
    0.96
    s
    0.96
    na
    0.95
    ement
    0.94
    ades
    0.94
    Activations Density 0.005%

    No Known Activations