© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31118
    Prev
    Next
    INDEX
    Explanations

    formula definitions

    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
    Present
    0.41
     File
    0.41
     MaterialApp
    0.41
    File
    0.40
    榃
    0.40
    Alcohol
    0.38
    Alexandra
    0.37
    ა
    0.37
    file
    0.37
     advised
    0.37
    POSITIVE LOGITS
    become
    0.41
     menjadi
    0.40
     becomes
    0.40
    becomes
    0.40
    stand
    0.38
     become
    0.37
     "_"
    0.37
     நிற
    0.37
     menunggu
    0.36
     जरूरतों
    0.36
    Activations Density 0.003%

    No Known Activations