© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 628
    Prev
    Next
    INDEX
    Explanations

    legal and technical jargon including statutes, rules, and coding terms

    oai_token-act-pair · gemini-2.0-flash

    number two

    np_max-act-logits · gemini-2.0-flash
    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
    SequentialGroup
    -0.86
    ="@+
    -0.76
    IVEREF
    -0.74
     Chwiliwch
    -0.73
    EndTag
    -0.72
    featureID
    -0.71
    SerializedSize
    -0.67
    Personendaten
    -0.67
     chi̍t
    -0.67
    CppCodeGen
    -0.66
    POSITIVE LOGITS
    2
    1.62
    ２
    1.07
     twenty
    1.05
     Twenty
    1.00
     TWENTY
    0.89
     ٢
    0.86
     ۲
    0.84
    ۲
    0.83
     २
    0.82
     ২
    0.82
    Activations Density 3.325%

    No Known Activations