© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    dose range, incidence, propensity score

    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
     कैप
    0.42
     Kap
    0.41
    Kap
    0.39
    を受
    0.39
     swag
    0.39
     w
    0.38
     Fraud
    0.38
     Folk
    0.38
     Gems
    0.37
     pod
    0.37
    POSITIVE LOGITS
     प्रांत
    0.38
    ም
    0.37
    Enroll
    0.37
     topik
    0.37
    MaxPool
    0.36
     prothorax
    0.35
     sala
    0.35
     છ
    0.35
     enrolled
    0.34
    SAL
    0.34
    Activations Density 0.071%

    No Known Activations