© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12514
    Prev
    Next
    INDEX
    Explanations

    words that could be parts of names.

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     iſt
    -1.34
    ſelves
    -1.29
     Monfieur
    -1.26
    ſelf
    -1.23
     pleaſure
    -1.20
     myſelf
    -1.16
     purpoſe
    -1.15
     auffi
    -1.14
     ſche
    -1.12
     Efq
    -1.12
    POSITIVE LOGITS
    .
    0.85
    ,
    0.82
    -
    0.77
     
    0.76
     (
    0.75
    (
    0.74
     in
    0.73
     U
    0.69
    ...
    0.66
    :
    0.64
    Activations Density 16.493%

    No Known Activations