© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93024
    Prev
    Next
    INDEX
    Explanations

    say 'ed' ending

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     for
    0.41
     cursing
    0.38
     -
    0.38
     by
    0.37
     having
    0.37
    มี
    0.37
     বলেছেন
    0.36
     –
    0.36
     -!
    0.36
    িয়েছেন
    0.36
    POSITIVE LOGITS
     Contribute
    0.66
     Construct
    0.61
     Estab
    0.57
     Establish
    0.57
     Introduce
    0.57
     Communic
    0.55
     Communicate
    0.55
     Evalu
    0.54
    '
    0.54
     Develop
    0.54
    Activations Density 0.001%

    No Known Activations