© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12233
    Prev
    Next
    INDEX
    Explanations

    code snippets from PHP files

    oai_token-act-pair · gemini-2.0-flash

    ORM, Query

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ScopeManager
    -0.60
    croll
    -0.58
    EndContext
    -0.56
    ApiProperty
    -0.56
    setVerticalGroup
    -0.54
     AppColors
    -0.50
    nościo
    -0.49
    urlpatterns
    -0.49
     setPrice
    -0.48
    leria
    -0.47
    POSITIVE LOGITS
    WithMany
    0.56
    żesz
    0.54
     ordinaires
    0.53
     isInitialized
    0.50
    JsonPropertyName
    0.47
    rophes
    0.47
    Française
    0.46
     normaux
    0.46
     بيها
    0.45
     дописавши
    0.45
    Activations Density 1.056%

    No Known Activations