© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16259
    Prev
    Next
    INDEX
    Explanations

    words used to describe electronic devices

    oai_token-act-pair · gemini-2.0-flash

    electronic circuits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    stdc
    -0.73
    databind
    -0.62
     Doi
    -0.57
     يتيمه
    -0.50
     Архів
    -0.50
    原始内容存档于
    -0.50
     DMCA
    -0.49
     FIM
    -0.48
     PAC
    -0.47
    inSlope
    -0.47
    POSITIVE LOGITS
    verwijspagina
    0.56
    ervazione
    0.56
     estimés
    0.55
    parsedMessage
    0.55
    principalTable
    0.54
     AssemblyCulture
    0.52
    niająca
    0.52
    Демографія
    0.52
    Focusing
    0.50
    AutoScaleMode
    0.50
    Activations Density 5.203%

    No Known Activations