© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12056
    Prev
    Next
    INDEX
    Explanations

    the word "implemented."

    oai_token-act-pair · gemini-2.0-flash

    implemented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     VIOL
    -0.54
    fromnode
    -0.52
    ImageContext
    -0.50
     onOptions
    -0.50
     esqu
    -0.47
    yn
    -0.47
    gr
    -0.47
    yc
    -0.47
    ValueStyle
    -0.46
    kens
    -0.46
    POSITIVE LOGITS
    <bos>
    1.40
     itſelf
    0.80
     myſelf
    0.74
     themſelves
    0.73
     raiſ
    0.72
     Monfieur
    0.69
    izational
    0.68
    omenclature
    0.68
    soever
    0.66
     pleaſure
    0.65
    Activations Density 1.304%

    No Known Activations