© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196246
    Prev
    Next
    INDEX
    Explanations

    teams, sports, flowering, identity

    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_15_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
     Tottenham
    0.18
    ഽ
    0.16
     정리
    0.15
     փ
    0.15
     ridges
    0.15
    瓤
    0.15
     이상
    0.15
     ridge
    0.15
    𝘻
    0.14
     फर्नीचर
    0.14
    POSITIVE LOGITS
    डू
    0.15
    ều
    0.14
    טן
    0.14
    üğünüz
    0.13
     वालों
    0.13
    ্রের
    0.13
    ון
    0.13
    ுக்
    0.13
    חר
    0.13
    ğin
    0.13
    Activations Density 0.003%

    No Known Activations