© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 44082
    Prev
    Next
    INDEX
    Explanations

    inventory management terms

    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_13_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
     inch
    0.51
    Ц
    0.48
     キ
    0.46
    扉
    0.44
     mop
    0.43
     deadlines
    0.43
     flint
    0.43
    James
    0.42
     ajo
    0.42
     নির্ভরশীল
    0.42
    POSITIVE LOGITS
    avay
    0.45
     खल
    0.42
    瘧
    0.41
    ంగ్
    0.40
     kolay
    0.40
    anil
    0.40
     Clothing
    0.40
     Ünivers
    0.40
     pérd
    0.39
    ွန်
    0.39
    Activations Density 0.033%

    No Known Activations