© 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. 12723
    Prev
    Next
    INDEX
    Explanations

    parentheses, special characters, numbers, and particular strings within mathematics or legal writing

    oai_token-act-pair · gemini-2.0-flash

    Code and legal language

    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
    I
    -1.07
    A
    -0.88
    J
    -0.72
    M
    -0.71
    B
    -0.69
    D
    -0.69
    L
    -0.68
    E
    -0.68
     noastre
    -0.66
    O
    -0.66
    POSITIVE LOGITS
     I
    0.85
     C
    0.79
     A
    0.79
     R
    0.78
     E
    0.77
     S
    0.76
     T
    0.76
     M
    0.75
     H
    0.75
     L
    0.74
    Activations Density 15.552%

    No Known Activations