© 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. 4100
    Prev
    Next
    INDEX
    Explanations

    seemingly random locations in the code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code and programming

    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
    3
    -0.66
     thither
    -0.50
    eaways
    -0.49
     favourably
    -0.49
    erequisites
    -0.48
    ashqai
    -0.48
     caudal
    -0.48
    σταση
    -0.47
     AssemblyProduct
    -0.47
    utives
    -0.46
    POSITIVE LOGITS
    principalColumn
    0.82
    تقاوى
    0.65
    StructEnd
    0.63
    addPreferredGap
    0.59
    WebVitals
    0.59
    #![
    0.59
    +#+#
    0.58
    Virus
    0.56
    interopRequire
    0.56
    bootstrapcdn
    0.56
    Activations Density 1.161%

    No Known Activations