© 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. 210460
    Prev
    Next
    INDEX
    Explanations

    dict patient

    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
     varieties
    0.41
     variété
    0.39
    𓈒
    0.38
     variedade
    0.38
    阠
    0.36
     variétés
    0.36
     Varieties
    0.36
    唋
    0.35
     връ
    0.35
    ストン
    0.34
    POSITIVE LOGITS
    dict
    0.43
    grapes
    0.43
    patient
    0.39
    dic
    0.38
     dict
    0.38
    ven
    0.37
     Dict
    0.37
    dangerous
    0.37
    patients
    0.37
    fuels
    0.37
    Activations Density 0.004%

    No Known Activations