© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 214184
    Prev
    Next
    INDEX
    Explanations

    drug names

    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_43_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
    Newman
    0.42
    peres
    0.40
    Paulo
    0.39
     Newman
    0.36
     Burroughs
    0.36
    ਊ
    0.35
     Happened
    0.35
    😱
    0.34
    Susan
    0.34
    Amino
    0.34
    POSITIVE LOGITS
     RAC
    0.48
    াত
    0.41
    HOLD
    0.41
     muod
    0.39
     rocket
    0.39
    भौ
    0.39
     Phuket
    0.39
     Luci
    0.38
     formas
    0.38
     सेव
    0.38
    Activations Density 0.015%

    No Known Activations