© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4707
    Prev
    Next
    INDEX
    Explanations

    source code and configuration snippets from various languages like Java, Python, XML, C++, and others.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash

    punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Cæsar
    -0.44
     Sopho
    -0.42
     Phoen
    -0.40
     Athenians
    -0.40
     Athenian
    -0.39
     Confucian
    -0.39
     Persians
    -0.38
     Negroes
    -0.38
     Haitian
    -0.38
     Protestantism
    -0.38
    POSITIVE LOGITS
      (
    0.52
    fören
    0.52
     détru
    0.50
    CHREIB
    0.50
    eſ
    0.50
     précédents
    0.50
     réfrig
    0.50
    Còn
    0.50
    FTFY
    0.48
     refroid
    0.48
    Activations Density 46.823%

    No Known Activations