© 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. 14644
    Prev
    Next
    INDEX
    Explanations

    code, including file paths and html

    oai_token-act-pair · gemini-2.0-flash

    code and file paths

    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
     (
    -0.40
     a
    -0.34
    (
    -0.34
     i
    -0.33
     new
    -0.32
     c
    -0.30
     C
    -0.30
     First
    -0.29
     v
    -0.29
     for
    -0.29
    POSITIVE LOGITS
    mybatisplus
    1.13
    djangoproject
    1.02
    parsedMessage
    0.98
    UserScript
    0.93
    WebServlet
    0.90
    artifactId
    0.88
    ioutil
    0.88
    JsonHelper
    0.87
    ibatis
    0.86
    UnitTesting
    0.86
    Activations Density 6.355%

    No Known Activations