© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153023
    Prev
    Next
    INDEX
    Explanations

    Alzheimer's disease

    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_23_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
     अल्लाह
    0.45
     암
    0.36
     stratification
    0.36
     аксессу
    0.36
    スメ
    0.35
     regurg
    0.35
    的总
    0.35
     mantle
    0.35
    客观
    0.35
    Qin
    0.35
    POSITIVE LOGITS
     turns
    0.47
     declarat
    0.44
     dichiar
    0.42
    čni
    0.41
    छ
    0.41
     service
    0.40
     escribe
    0.40
    turns
    0.40
     cruisers
    0.40
     selv
    0.40
    Activations Density 0.001%

    No Known Activations