© 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. 1951
    Prev
    Next
    INDEX
    Explanations

    snippets of code and text related to error debugging

    oai_token-act-pair · gemini-2.0-flash

    Terminal commands

    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
     EconPapers
    -0.93
     mapStateToProps
    -0.68
    ValueStyle
    -0.64
     Meksiku
    -0.62
     ويكيپيديا
    -0.57
     Huey
    -0.57
     beginnetje
    -0.57
     Reſ
    -0.56
    calientes
    -0.55
     Houſe
    -0.55
    POSITIVE LOGITS
     command
    1.41
     Command
    1.19
    command
    1.19
    Command
    1.08
     cmd
    1.07
    cmd
    1.05
    コマンド
    1.02
     terminal
    1.00
     commands
    0.98
    命令
    0.96
    Activations Density 1.698%

    No Known Activations