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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8419
    Prev
    Next
    INDEX
    Explanations

    the word "tasks" and words ending in "-ed"

    oai_token-act-pair · gemini-2.0-flash

    tasks

    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
    ,
    -1.37
     and
    -1.18
    <bos>
    -1.17
     
    -1.16
    2
    -1.16
    ↵
    -1.15
    .
    -1.13
    -
    -1.11
    1
    -1.09
    I
    -1.09
    POSITIVE LOGITS
     Efq
    2.03
     $_"
    1.85
     Theſe
    1.83
    ^(@)
    1.75
     myſelf
    1.74
     Monfieur
    1.73
     doubtnut
    1.70
     Majefty
    1.69
     iſt
    1.64
    .}~\
    1.63
    Activations Density 0.451%

    No Known Activations