© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8420
    Prev
    Next
    INDEX
    Explanations

    source code, math formulas, or website addresses

    oai_token-act-pair · gemini-2.0-flash

    Code and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     S
    -0.60
     N
    -0.57
     Big
    -0.56
     [
    -0.56
     I
    -0.55
     M
    -0.55
     L
    -0.54
     s
    -0.54
     E
    -0.54
     H
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.80
     AssemblyProduct
    0.76
     invokingState
    0.75
    AndEndTag
    0.75
     MenuView
    0.75
    GEBURTSDATUM
    0.73
     BitmapFactory
    0.73
    +:+
    0.72
    StoryboardSegue
    0.71
    OGND
    0.71
    Activations Density 2.937%

    No Known Activations