© 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. 52306
    Prev
    Next
    INDEX
    Explanations

    kilometers and meters

    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
    选题
    0.39
     Networking
    0.39
    簋
    0.38
     networking
    0.37
     numberOf
    0.36
    Networking
    0.36
     Surveillance
    0.36
    veillance
    0.36
    Lifecycle
    0.35
     పరీ
    0.35
    POSITIVE LOGITS
     tuberc
    0.40
    っぽ
    0.37
    umus
    0.37
     प्रो
    0.36
    በረ
    0.36
    ģ
    0.36
    すぎる
    0.35
    Must
    0.34
    すぎて
    0.34
     tig
    0.33
    Activations Density 0.004%

    No Known Activations