© 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. 16138
    Prev
    Next
    INDEX
    Explanations

    punctuation marks appearing at the end of a sentence, or is otherwise strongly activated by bulleted lists and information intended to help or guide the reader

    oai_token-act-pair · gemini-2.0-flash

    question words

    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
    ThroughAttribute
    -0.65
    Said
    -0.59
    ⓧ
    -0.59
     Nod
    -0.57
    OGND
    -0.56
    Nod
    -0.55
     Others
    -0.54
    complexContent
    -0.54
    MemoryWarning
    -0.54
     Said
    -0.53
    POSITIVE LOGITS
     How
    1.34
    How
    1.13
     What
    1.06
     Why
    0.95
     Who
    0.92
     Where
    0.89
    What
    0.86
    Who
    0.84
    Why
    0.76
     Which
    0.75
    Activations Density 6.785%

    No Known Activations