© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203176
    Prev
    Next
    INDEX
    Explanations

    DELETE operations

    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_37_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
     Möbius
    0.46
     Miniature
    0.44
     testimony
    0.41
    SetFloat
    0.40
     miniature
    0.40
    ں
    0.39
     primers
    0.39
     miniatur
    0.39
     কৃতিত্ব
    0.38
    usiasm
    0.38
    POSITIVE LOGITS
     DELETE
    0.41
     dissolution
    0.40
    HttpDelete
    0.40
    ENDPOINT
    0.40
    煮
    0.40
    Cherry
    0.37
    弃
    0.37
    蜜
    0.37
     declared
    0.36
    HTTP
    0.36
    Activations Density 0.000%

    No Known Activations