© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44834
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions ("a", "for")

    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_22_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
     same
    0.39
     expanded
    0.38
     simply
    0.38
     trading
    0.37
    p
    0.37
     exploits
    0.37
    cidas
    0.37
     greener
    0.36
    c
    0.36
    ustain
    0.35
    POSITIVE LOGITS
    于是
    0.51
    呚
    0.43
     სი
    0.42
     உடனடியாக
    0.42
     因此
    0.42
    䚺
    0.42
     đứa
    0.41
     সুতরাং
    0.40
     امتحان
    0.40
    於是
    0.40
    Activations Density 0.006%

    No Known Activations