© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4643
    Prev
    Next
    INDEX
    Explanations

    words in the context of something "being used."

    oai_token-act-pair · gemini-2.0-flash

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     used
    -2.42
    Used
    -2.11
    <bos>
    -2.11
     Used
    -2.08
    used
    -2.08
     USED
    -1.88
    USED
    -1.45
     usado
    -1.42
     utilisé
    -1.41
     utilizado
    -1.38
    POSITIVE LOGITS
    adaran
    0.59
    ChildScrollView
    0.56
    hdashline
    0.55
     >=",
    0.55
    atigable
    0.55
    RepeatedField
    0.55
     DialogInterface
    0.54
    wanderung
    0.54
     ListTile
    0.52
    matico
    0.52
    Activations Density 1.883%

    No Known Activations