© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234272
    Prev
    Next
    INDEX
    Explanations

    instability

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    岡
    0.37
    Dame
    0.36
     Extremely
    0.36
    extremely
    0.35
    寸法
    0.35
    挖掘
    0.35
    tss
    0.35
     Patton
    0.35
     estremamente
    0.35
    㐫
    0.35
    POSITIVE LOGITS
     drove
    0.45
    Pl
    0.43
     النمو
    0.43
     Nand
    0.43
     convection
    0.42
     Plas
    0.42
     drive
    0.41
     операций
    0.41
     East
    0.40
     growth
    0.40
    Activations Density 0.001%

    No Known Activations