© 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. 16219
    Prev
    Next
    INDEX
    Explanations

    code, special characters, and table formatting with numbers

    oai_token-act-pair · gemini-2.0-flash

    Four/4

    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
    Rhestr
    -0.61
    DebuggerNonUser
    -0.56
    WebElementEntity
    -0.56
    ImageContext
    -0.49
     bezeichneter
    -0.48
     Wednesday
    -0.48
    ༘
    -0.48
    Przypisy
    -0.47
     getItemId
    -0.47
    setopt
    -0.47
    POSITIVE LOGITS
     Four
    1.91
     four
    1.90
    4
    1.78
    four
    1.74
    Four
    1.73
     FOUR
    1.62
    FOUR
    1.57
    四
    1.54
     Fourth
    1.53
     fourth
    1.51
    Activations Density 19.726%

    No Known Activations