© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10247
    Prev
    Next
    INDEX
    Explanations

    the word "back" or phrases like "get back".

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "back"

    np_token-act-pair-logits · gpt-4o-mini

    back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    hoga
    -0.72
    WireFormat
    -0.69
     autorytatywna
    -0.65
    clusal
    -0.65
    retanto
    -0.58
     MHD
    -0.58
     MongoClient
    -0.58
    Opposition
    -0.57
     Italijani
    -0.57
    expandindo
    -0.57
    POSITIVE LOGITS
     on
    0.61
     defaultstate
    0.50
    '}),
    0.46
     in
    0.46
     home
    0.42
    "]];
    0.41
    ைய
    0.40
    ある
    0.40
    complexContent
    0.39
    Phương
    0.39
    Activations Density 0.338%

    No Known Activations