© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51628
    Prev
    Next
    INDEX
    Explanations

    leave feeling

    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_31_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
    obec
    0.32
     Aden
    0.31
    ational
    0.31
     Carson
    0.31
    辏
    0.30
    apt
    0.30
    fun
    0.30
    ็จ
    0.30
    彰
    0.30
    ত্ম
    0.29
    POSITIVE LOGITS
    テイ
    0.38
    煒
    0.33
     जाति
    0.32
     envisage
    0.32
     चमकदार
    0.32
    িগ
    0.31
     வாக்க
    0.31
     uitvo
    0.31
     bolt
    0.30
     ಬೆ
    0.30
    Activations Density 0.001%

    No Known Activations