© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14846
    Prev
    Next
    INDEX
    Explanations

    code-related content such as function calls, variable names, and code elements

    oai_token-act-pair · gemini-2.0-flash

    code/data files

    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
     Permanent
    -0.88
     Low
    -0.87
     Global
    -0.82
     High
    -0.82
     Large
    -0.81
     Small
    -0.80
     Normal
    -0.80
     Intermediate
    -0.78
     Basic
    -0.78
     Common
    -0.78
    POSITIVE LOGITS
     يتيمه
    0.65
     Assays
    0.62
     propOrder
    0.60
     Says
    0.60
     Tells
    0.57
     Songs
    0.56
     Drinks
    0.55
     AssemblyVersion
    0.54
     Picchu
    0.54
     Offerings
    0.53
    Activations Density 12.818%

    No Known Activations