© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99974
    Prev
    Next
    INDEX
    Explanations

    dildo insertion, POC, Kung Pao Chicken

    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_14_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
    絠
    0.53
    Accelerator
    0.50
    ovenant
    0.50
    క్టర్
    0.50
    <(
    0.50
     महंत
    0.49
     deacon
    0.49
    ंत
    0.49
    Buffer
    0.48
     IUE
    0.48
    POSITIVE LOGITS
    </caption>
    0.52
     насе
    0.45
     відста
    0.45
    모
    0.44
    沪
    0.43
     집
    0.43
    ма
    0.43
     estreno
    0.43
    上げ
    0.42
    blogger
    0.42
    Activations Density 0.000%

    No Known Activations