© 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. 11475
    Prev
    Next
    INDEX
    Explanations

    words relevant to recipes and scientific research.

    oai_token-act-pair · gemini-2.0-flash

    any

    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
    IonicModule
    -0.54
    ussis
    -0.50
     WebApplication
    -0.48
    BASEPATH
    -0.46
     CURLOPT
    -0.46
    Abitanti
    -0.45
    ApiOperation
    -0.45
    setupUi
    -0.43
    Тогда
    -0.43
    ynb
    -0.42
    POSITIVE LOGITS
     any
    3.28
    Any
    2.80
     Any
    2.73
    any
    2.69
     ANY
    2.31
    ANY
    2.20
    任何
    2.16
     cualquier
    2.08
     qualquer
    2.06
     Cualquier
    1.87
    Activations Density 5.252%

    No Known Activations