© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11731
    Prev
    Next
    INDEX
    Explanations

    language related to coordinate measurement machines and articulated arms

    oai_token-act-pair · gemini-2.0-flash

    arm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InvalidProtocol
    -0.73
     AssemblyCulture
    -0.72
    InSection
    -0.69
     MessageBoxIcon
    -0.64
    loài
    -0.63
    Espèce
    -0.61
    цездатний
    -0.61
     Bioaccumulative
    -0.60
     ILogger
    -0.56
     Finlande
    -0.56
    POSITIVE LOGITS
     arm
    0.93
    arm
    0.77
     arms
    0.75
     Arm
    0.71
     boom
    0.71
     braccio
    0.70
     brazo
    0.70
    Arm
    0.69
     brazos
    0.69
     lengan
    0.68
    Activations Density 1.659%

    No Known Activations