© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10298
    Prev
    Next
    INDEX
    Explanations

    seemingly disparate concepts from science, politics and medicine.

    oai_token-act-pair · gemini-2.0-flash

    mechanical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Gra
    -0.47
     wave
    -0.46
     Mou
    -0.43
    wave
    -0.42
     gra
    -0.42
    msgid
    -0.42
    enumeration
    -0.41
     link
    -0.41
     corren
    -0.40
    änger
    -0.40
    POSITIVE LOGITS
    UnusedPrivate
    1.09
     ProtoMessage
    0.85
     Exacts
    0.85
    IUrlHelper
    0.76
     protoimpl
    0.73
     }{@
    0.72
    ⓧ
    0.71
    ThroughAttribute
    0.70
     ApiException
    0.69
    antMatchers
    0.69
    Activations Density 3.963%

    No Known Activations