© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    the word "therapy", often also in conjunction with "physical"

    oai_token-act-pair · gemini-2.0-flash

    therapy

    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
     Cæsar
    -1.34
     cauſe
    -1.28
     Monfieur
    -1.25
     Majefty
    -1.24
     Shakspeare
    -1.21
     vectorielle
    -1.20
     Anſ
    -1.20
     vectorielles
    -1.18
     Houſe
    -1.17
     Efq
    -1.17
    POSITIVE LOGITS
     The
    0.75
     A
    0.74
    <eos>
    0.71
     the
    0.69
     At
    0.66
     
    0.65
     in
    0.63
     Bon
    0.63
     An
    0.62
     Per
    0.61
    Activations Density 0.940%

    No Known Activations