© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4098
    Prev
    Next
    INDEX
    Explanations

    memory usage or class loading

    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_39_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
     annuity
    0.41
     dhamme
    0.41
    MJX
    0.40
    ñones
    0.40
     prisms
    0.39
     CIRCA
    0.39
     bolso
    0.38
    ﻵ
    0.38
     SEG
    0.37
     disposiciones
    0.37
    POSITIVE LOGITS
     try
    0.42
    第二天
    0.39
    try
    0.37
    열
    0.37
    ücks
    0.35
    oléon
    0.34
    gan
    0.34
    getResource
    0.34
     Nasir
    0.34
     Creators
    0.34
    Activations Density 0.000%

    No Known Activations