© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14038
    Prev
    Next
    INDEX
    Explanations

    technical documentation and data, possibly related to processes and measurements.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AttributeSet
    -0.67
     getopt
    -0.65
    PerformLayout
    -0.57
    owna
    -0.55
    ImageContext
    -0.54
    ViewImports
    -0.54
    BeginContext
    -0.51
    ine
    -0.51
    antart
    -0.51
    Referencie
    -0.51
    POSITIVE LOGITS
    (!__
    0.59
     تانيه
    0.55
    epar
    0.52
     imb
    0.47
    ạt
    0.47
    τέλε
    0.47
    dek
    0.47
    ringed
    0.46
    arka
    0.46
    bul
    0.46
    Activations Density 12.712%

    No Known Activations