© 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. 32084
    Prev
    Next
    INDEX
    Explanations

    medications or drugs

    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
     Hessian
    0.44
    ttf
    0.43
    ന്ത്രി
    0.41
     በሽታ
    0.41
     단위
    0.40
    ropolis
    0.39
     ईद
    0.38
    弾
    0.38
     모집
    0.38
     벡터
    0.37
    POSITIVE LOGITS
     ral
    0.46
     digoxin
    0.46
     clor
    0.45
     praz
    0.44
     itr
    0.44
     Prop
    0.42
    Dic
    0.42
     lor
    0.42
     Pemb
    0.42
    chlor
    0.42
    Activations Density 0.054%

    No Known Activations