© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10996
    Prev
    Next
    INDEX
    Explanations

    legal jargon, acronyms, and references to official institutions

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    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
     Pose
    -0.82
     Iter
    -0.82
     Dere
    -0.81
     Repar
    -0.80
     Dens
    -0.79
     Stem
    -0.79
     Favor
    -0.79
     Propag
    -0.79
     Tend
    -0.79
     Oper
    -0.78
    POSITIVE LOGITS
    D
    0.40
    B
    0.39
    X
    0.38
    N
    0.38
    H
    0.36
    C
    0.36
    K
    0.35
    O
    0.35
    F
    0.35
    T
    0.34
    Activations Density 5.713%

    No Known Activations