© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51486
    Prev
    Next
    INDEX
    Explanations

    places to buy things

    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_30_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
     signOut
    0.30
     signos
    0.29
    Signing
    0.29
    场景
    0.29
     Cheung
    0.29
     znak
    0.29
     Signing
    0.28
     꿈
    0.28
    SignedIn
    0.28
    壅
    0.27
    POSITIVE LOGITS
     सांसदों
    0.31
     حلقه
    0.30
     MPs
    0.30
     td
    0.29
     địa
    0.29
     Expert
    0.28
    द्वी
    0.28
     dai
    0.27
     comprehensively
    0.27
     purchased
    0.27
    Activations Density 0.007%

    No Known Activations