© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42515
    Prev
    Next
    INDEX
    Explanations

    luminosity and color variations

    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_13_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
    Gs
    0.25
    Vienna
    0.24
    G
    0.24
    Site
    0.24
    Glucose
    0.24
    Glare
    0.24
    Gym
    0.22
    Sunglasses
    0.22
    Bs
    0.21
    Locator
    0.21
    POSITIVE LOGITS
    ↵
    0.22
     ceded
    0.21
     deleg
    0.20
     relinquish
    0.20
     direito
    0.20
     debo
    0.20
     прав
    0.19
     hâ
    0.19
     kula
    0.19
     j
    0.19
    Activations Density 0.003%

    No Known Activations