© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136792
    Prev
    Next
    INDEX
    Explanations

    SwiftUI View

    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_37_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
     banned
    0.46
     outlaw
    0.41
    textarea
    0.39
    Compet
    0.39
     banning
    0.39
    Atoi
    0.38
    }}]{
    0.37
     سانس
    0.37
    솔
    0.37
     आंसर
    0.37
    POSITIVE LOGITS
     Rodr
    0.46
     Pav
    0.38
     Oy
    0.38
    gav
    0.37
     discard
    0.36
     scepticism
    0.36
    žen
    0.36
     Biomedical
    0.36
     ensamb
    0.35
     smoothing
    0.35
    Activations Density 0.000%

    No Known Activations