© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147621
    Prev
    Next
    INDEX
    Explanations

    body image issues

    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_18_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
    ience
    0.54
    ...",
    0.51
    config
    0.50
     &
    0.48
     team
    0.48
    com
    0.48
    …
    0.48
     -
    0.48
    ical
    0.47
     /
    0.47
    POSITIVE LOGITS
    लक्ष्मी
    0.55
     Сасик
    0.54
     पुरस्कृत
    0.52
    ྗ
    0.51
    वरणीय
    0.50
    𝙰
    0.50
     wikipagina
    0.48
    羞
    0.48
     बरबाद
    0.48
     도형
    0.47
    Activations Density 0.003%

    No Known Activations