Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13372
    Prev
    Next
    INDEX
    Explanations

    mentions of programming code and legal or logical "fore/below/following" references

    oai_token-act-pair · gemini-2.0-flash

    Code and legal documents

    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
    ]='\
    -1.00
    StoryboardSegue
    -1.00
    AndEndTag
    -0.97
    DockStyle
    -0.95
    tvguidetime
    -0.88
     صوتيه
    -0.87
    makeConstraints
    -0.85
     كومونز
    -0.84
     onCancelled
    -0.84
     intptr
    -0.75
    POSITIVE LOGITS
     below
    0.96
    below
    0.75
     Below
    0.75
    Below
    0.75
     above
    0.72
     abaixo
    0.69
     following
    0.64
    Listed
    0.61
    above
    0.59
    <bos>
    0.56
    Activations Density 0.916%

    No Known Activations