© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135227
    Prev
    Next
    INDEX
    Explanations

    become, becoming, became

    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
    uencia
    0.43
    ಅ
    0.37
    uyentes
    0.37
    नेस
    0.37
    ស្រាយ
    0.36
    जूदा
    0.35
     tors
    0.35
    ampshire
    0.35
     Hampshire
    0.35
     $\#
    0.34
    POSITIVE LOGITS
     become
    1.27
     becoming
    1.14
     became
    1.12
     divent
    1.08
     Become
    1.07
    Become
    1.05
    become
    1.05
     becomes
    1.05
     diventare
    0.99
     devenir
    0.98
    Activations Density 0.176%

    No Known Activations