© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5007
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes and advice about navigating difficult situations involving faith and family.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     natal
    -0.72
    getCause
    -0.63
    Ecotoxicity
    -0.61
    NUMX
    -0.60
     autobiography
    -0.60
     ISTAT
    -0.55
    SerializedSize
    -0.55
     wireType
    -0.55
    참고
    -0.55
    Composable
    -0.54
    POSITIVE LOGITS
     pinulongan
    0.55
    expandindo
    0.49
    jsonwebtoken
    0.49
    InputTagHelper
    0.49
     venons
    0.48
    /***/
    0.48
    期刊论文
    0.45
    DataSnapshot
    0.44
    mathcal
    0.42
     cherchés
    0.42
    Activations Density 1.204%

    No Known Activations