© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14233
    Prev
    Next
    INDEX
    Explanations

    reports of analysis or data collection in a scientific study

    oai_token-act-pair · gemini-2.0-flash

    reporting findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    DoubleQuotes
    -0.60
     moschino
    -0.58
    ListModule
    -0.57
     Bourgoin
    -0.51
     Imports
    -0.51
     Ulysses
    -0.50
     sanitaria
    -0.50
    )];
    -0.50
     Crus
    -0.50
     Suez
    -0.49
    POSITIVE LOGITS
    NewUrlParser
    0.63
     AttributeSet
    0.59
    Javadoc
    0.56
     estekak
    0.55
    ыгана
    0.54
    الحياه
    0.52
     diminuer
    0.52
    ynb
    0.51
    putBoolean
    0.51
    ransition
    0.51
    Activations Density 17.148%

    No Known Activations