© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 203452
    Prev
    Next
    INDEX
    Explanations

    priceless, price, worth

    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_37_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
    ڑوں
    0.40
     مرف
    0.40
    ائط
    0.39
     முனை
    0.38
    ሟ
    0.38
    位
    0.37
    tox
    0.36
     movingRect
    0.36
     punctured
    0.36
     位
    0.36
    POSITIVE LOGITS
     priceless
    1.99
     Pric
    1.64
    pric
    1.59
     PRICE
    1.30
     invaluable
    1.24
     price
    1.15
    PRICE
    1.12
     Price
    1.09
     pric
    1.06
    Price
    1.05
    Activations Density 0.001%

    No Known Activations