© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 77995
    Prev
    Next
    INDEX
    Explanations

    challenges and limitations

    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
    损坏
    0.40
     dañ
    0.36
    ocyanate
    0.34
    ライ
    0.32
     даже
    0.32
    ([])
    0.31
    сек
    0.31
    Off
    0.30
     storyline
    0.30
     딱
    0.30
    POSITIVE LOGITS
     gand
    0.38
    滹
    0.37
     Locomotive
    0.36
     Ran
    0.35
    仠
    0.35
    தெ
    0.35
     soprav
    0.35
     Gand
    0.34
     limiti
    0.34
     قلنا
    0.34
    Activations Density 0.012%

    No Known Activations