© 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. 117220
    Prev
    Next
    INDEX
    Explanations

    `@`, `Helper`, `if`, `Note`, `Generate`, `export`

    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
    other
    0.41
    TM
    0.41
    Bar
    0.40
    8
    0.38
    anyu
    0.38
    hr
    0.37
    essen
    0.37
    ymen
    0.37
    lw
    0.37
    MW
    0.37
    POSITIVE LOGITS
    तीने
    0.45
    𒀉
    0.44
     aang
    0.43
     stanie
    0.42
     ኢ
    0.41
     pédicule
    0.41
     phản
    0.40
     фестива
    0.39
     問題
    0.39
     niên
    0.39
    Activations Density 0.000%

    No Known Activations