© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247170
    Prev
    Next
    INDEX
    Explanations

    words following 'as' or 'over'

    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_40_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
    Comparing
    0.39
     націона
    0.38
    শিক্ষা
    0.37
    Individual
    0.37
    meck
    0.37
    Comparison
    0.36
    𒈨
    0.36
    COMPAR
    0.35
    comparing
    0.35
     comparing
    0.35
    POSITIVE LOGITS
     স্নাত
    0.40
     Lee
    0.38
    డు
    0.36
     সফদর
    0.35
     Kef
    0.35
     pervasive
    0.35
     onset
    0.34
    దిక
    0.34
     Spi
    0.34
    വ
    0.33
    Activations Density 0.002%

    No Known Activations