© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236234
    Prev
    Next
    INDEX
    Explanations

    differential privacy, inference, privacy

    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_32_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
    dim
    0.42
     przedstaw
    0.40
     Convex
    0.40
     ဒါ
    0.40
    ≺
    0.38
     kond
    0.38
    frag
    0.38
    ěru
    0.38
     présentant
    0.37
    dro
    0.37
    POSITIVE LOGITS
     इंटरेस्ट
    0.37
     intenso
    0.35
    {-
    0.34
     उतार
    0.34
    ("(
    0.34
    けると
    0.34
    Interest
    0.33
    hidupan
    0.33
    髦
    0.33
     اختی
    0.32
    Activations Density 0.006%

    No Known Activations