© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    words related to practical advice, problem solving or requests for assistance

    oai_token-act-pair · gemini-2.0-flash

    Programming/data handling contexts

    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
    letoe
    -0.52
    ParallelGroup
    -0.50
     فريبيس
    -0.47
    pyrene
    -0.46
    Twas
    -0.46
    녕
    -0.45
    liesslich
    -0.43
    着用
    -0.42
     mukana
    -0.42
    artney
    -0.41
    POSITIVE LOGITS
    enumi
    0.70
     pulumi
    0.58
     ujednoznacz
    0.57
    aarrggbb
    0.53
     linkovi
    0.52
     yourself
    0.52
    OutputType
    0.52
    XtraGrid
    0.51
     оригіналу
    0.51
    DebuggerStep
    0.51
    Activations Density 2.445%

    No Known Activations