© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13866
    Prev
    Next
    INDEX
    Explanations

    parts of code pertaining to data or arguments

    oai_token-act-pair · gemini-2.0-flash

    Parentheses

    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
    Bricks
    -0.42
    Cols
    -0.40
    fashioned
    -0.39
    Nums
    -0.36
     Rooms
    -0.36
     daß
    -0.36
     kebun
    -0.36
     ROOMS
    -0.36
    Fields
    -0.35
    Hooks
    -0.35
    POSITIVE LOGITS
    XmlAccessType
    0.79
     AssemblyCulture
    0.71
    imageshack
    0.71
    ChildScrollView
    0.68
     SafeMath
    0.68
    LabelTagHelper
    0.67
     CreateTagHelper
    0.67
    ConverterFactory
    0.66
    IndentedString
    0.66
    indications
    0.66
    Activations Density 11.926%

    No Known Activations