© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10868
    Prev
    Next
    INDEX
    Explanations

    references to personal anecdotes and observations

    oai_token-act-pair · gemini-2.0-flash

    this that

    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
     this
    -0.58
    gatsby
    -0.53
    этому
    -0.49
    ↵
    -0.48
     That
    -0.48
     diesem
    -0.48
     cette
    -0.47
    That
    -0.47
    THAT
    -0.47
     esa
    -0.45
    POSITIVE LOGITS
     незавершена
    1.04
    AndEndTag
    0.84
     betweenstory
    0.76
     resourceCulture
    0.76
     AssemblyCulture
    0.75
    ISupport
    0.74
    ValueStyle
    0.73
    Datuak
    0.70
    Geplaatst
    0.70
    Portale
    0.69
    Activations Density 10.979%

    No Known Activations