© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151247
    Prev
    Next
    INDEX
    Explanations

    presented, paper, work, conducted, offered

    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_23_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
     conquista
    0.41
     createTask
    0.36
    currentCharacter
    0.33
     conquist
    0.33
     conquistar
    0.33
     Бекер
    0.33
     завое
    0.33
    酘
    0.32
    畅
    0.32
     las
    0.32
    POSITIVE LOGITS
    report
    0.38
     റിപ്പോ
    0.38
     लिहाज
    0.37
     report
    0.35
     folded
    0.34
    count
    0.34
    fine
    0.34
     unfolded
    0.33
    look
    0.33
     pressed
    0.32
    Activations Density 0.001%

    No Known Activations