© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8092
    Prev
    Next
    INDEX
    Explanations

    personal blog style text discussing current activities.

    oai_token-act-pair · gemini-2.0-flash

    Expressing thoughts/opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    -0.68
     AssemblyCompany
    -0.67
    BufferException
    -0.67
    tagext
    -0.65
    tisseur
    -0.64
     sauvages
    -0.62
    IsContent
    -0.62
     internationales
    -0.62
    PerformLayout
    -0.59
    BeginContext
    -0.59
    POSITIVE LOGITS
     needs
    0.48
    Зноскі
    0.44
     quad
    0.44
    .
    0.43
    iostream
    0.42
    vice
    0.42
    áló
    0.41
     non
    0.41
     whisper
    0.40
     BBA
    0.40
    Activations Density 13.065%

    No Known Activations