© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15784
    Prev
    Next
    INDEX
    Explanations

    the word "there", particularly when accompanied by words indicating existence or conditions

    oai_token-act-pair · gemini-2.0-flash

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AnimationsModule
    -0.60
     estekak
    -0.58
     scorso
    -0.56
     pères
    -0.53
    "]];
    -0.53
    __':
    -0.52
    "}},
    -0.51
     esclu
    -0.51
    >())
    -0.51
    prnewswire
    -0.50
    POSITIVE LOGITS
     certainly
    0.55
    is
    0.55
     استنادى
    0.51
     CommandType
    0.49
    isl
    0.48
     ProtoMessage
    0.48
    getOutputStream
    0.47
    WebVitals
    0.47
    JoinTable
    0.47
    ’
    0.46
    Activations Density 14.717%

    No Known Activations