© 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. 3861
    Prev
    Next
    INDEX
    Explanations

    testimony, being a witness to an event, judgment

    oai_token-act-pair · gemini-2.0-flash

    witness

    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
     Monfieur
    -1.40
     myſelf
    -1.38
     Theſe
    -1.35
     Efq
    -1.34
     themſelves
    -1.28
     houſe
    -1.28
     itſelf
    -1.26
     Houſe
    -1.24
     leaſt
    -1.20
     faſt
    -1.20
    POSITIVE LOGITS
    SequentialGroup
    0.69
     en
    0.63
     del
    0.62
     li
    0.61
     m
    0.61
     y
    0.61
     <
    0.60
     d
    0.60
     (
    0.60
     null
    0.59
    Activations Density 1.883%

    No Known Activations