© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11896
    Prev
    Next
    INDEX
    Explanations

    descriptive words in a product description and dashed lines

    oai_token-act-pair · gemini-2.0-flash

    Code/Technical 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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     wireType
    -0.77
    SharedCtor
    -0.74
    parsedMessage
    -0.72
     <",
    -0.68
    featureID
    -0.63
    webElement
    -0.60
    gameserver
    -0.59
     @"/
    -0.58
     disambiguazione
    -0.58
    getDescriptor
    -0.56
    POSITIVE LOGITS
    UpInside
    0.50
    äden
    0.48
     Aug
    0.48
     protected
    0.47
    IActionResult
    0.47
     onStop
    0.45
    ראה
    0.44
    stdio
    0.43
     Frost
    0.43
    HIT
    0.43
    Activations Density 6.465%

    No Known Activations