© 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. 10632
    Prev
    Next
    INDEX
    Explanations

    terms related to the economy, computers, personal or environmental health, shipping, politics, and/or taxes.

    oai_token-act-pair · gemini-2.0-flash

    problems

    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
     major
    -0.57
    Real
    -0.56
     Real
    -0.56
    lietta
    -0.53
    images
    -0.52
    xdr
    -0.49
     Photos
    -0.49
     BrowserModule
    -0.49
     Power
    -0.48
    zame
    -0.48
    POSITIVE LOGITS
     متعلقه
    1.01
    InjectAttribute
    0.84
     تانيه
    0.77
     الحره
    0.71
     BoxFit
    0.67
     nahilalakip
    0.65
     виправивши
    0.65
     صوتيه
    0.64
    henswürdigkeiten
    0.64
     '\\;'
    0.64
    Activations Density 5.863%

    No Known Activations