© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15334
    Prev
    Next
    INDEX
    Explanations

    a variety of keywords related to actions and states of being, especially "do", "this", and related words.

    oai_token-act-pair · gemini-2.0-flash

    do

    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
    +#+#
    -1.34
     otomatig
    -0.90
     Theſe
    -0.87
    gbaar
    -0.83
     fhew
    -0.81
     PeEnEo
    -0.81
     myſelf
    -0.79
    thâu
    -0.79
     himo
    -0.79
     Efq
    -0.79
    POSITIVE LOGITS
     to
    0.69
     also
    0.59
     for
    0.58
     from
    0.55
     in
    0.54
     on
    0.53
    .
    0.53
    ,
    0.49
     with
    0.47
    ...
    0.47
    Activations Density 9.197%

    No Known Activations