© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206048
    Prev
    Next
    INDEX
    Explanations

    Instagram bot communication

    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
     argued
    0.38
     debated
    0.37
    Ug
    0.37
     Durand
    0.37
    彝
    0.37
    鉄道
    0.37
    㐱
    0.37
     elemen
    0.36
     therapeut
    0.36
    獧
    0.35
    POSITIVE LOGITS
    search
    0.61
    搜索
    0.59
     search
    0.57
     সার্চ
    0.55
    検索
    0.54
     Facebook
    0.53
     searches
    0.52
     सर्च
    0.52
     hashtags
    0.52
    搜尋
    0.52
    Activations Density 0.002%

    No Known Activations