© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163512
    Prev
    Next
    INDEX
    Explanations

    Ocean

    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_31_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
    ารถ
    0.40
     منطقة
    0.40
    ของ
    0.38
     वर्गी
    0.38
    人士
    0.37
    ='"
    0.36
     demandes
    0.36
     উদ্যোগ
    0.36
    ִ
    0.36
    ளி
    0.35
    POSITIVE LOGITS
    ypi
    0.42
    PageState
    0.38
    nym
    0.36
     fortunate
    0.36
     wall
    0.35
    inaldo
    0.35
    ikulum
    0.35
    üre
    0.34
    impinan
    0.34
     DataType
    0.34
    Activations Density 0.004%

    No Known Activations