© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63348
    Prev
    Next
    INDEX
    Explanations

    academic subjects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     pre
    0.44
    school
    0.43
    pre
    0.43
    预
    0.40
     स्कूल
    0.39
    guess
    0.39
     શિક્ષ
    0.38
     Pre
    0.38
    new
    0.37
     получать
    0.37
    POSITIVE LOGITS
     subj
    0.40
     업
    0.40
     général
    0.40
     Instruction
    0.39
     مفه
    0.39
    鏟
    0.38
     générale
    0.38
     generalization
    0.38
    乱流
    0.38
    ផ្គ
    0.38
    Activations Density 0.000%

    No Known Activations