© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10679
    Prev
    Next
    INDEX
    Explanations

    solve_ program

    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_40_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
    蓍
    0.44
    Jorge
    0.43
     Jeg
    0.38
    formal
    0.38
     JG
    0.38
    Jeg
    0.38
     Heg
    0.38
     popula
    0.37
     हिर
    0.37
     Jorge
    0.36
    POSITIVE LOGITS
    RATE
    0.41
    इनस
    0.41
    招
    0.40
    Transition
    0.38
     using
    0.38
    ascus
    0.38
     Transition
    0.37
    oral
    0.37
     elevating
    0.36
    लू
    0.35
    Activations Density 0.001%

    No Known Activations