© 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. 4949
    Prev
    Next
    INDEX
    Explanations

    the occurrence of someone being present, especially in a legal or official context

    oai_token-act-pair · gemini-2.0-flash

    presence

    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
     houſe
    -0.84
     myſelf
    -0.82
     poffible
    -0.76
     purpoſe
    -0.76
     faſt
    -0.75
     Efq
    -0.73
     uſe
    -0.72
     ſte
    -0.71
     ſmall
    -0.71
     ſche
    -0.71
    POSITIVE LOGITS
     referenties
    1.09
    AddTagHelper
    0.78
    <bos>
    0.71
     שוליים
    0.65
    AccessorTable
    0.64
     BorderRadius
    0.64
    AndEndTag
    0.59
     GenerationType
    0.59
    preventDefault
    0.56
     StatelessWidget
    0.56
    Activations Density 1.099%

    No Known Activations