© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4184
    Prev
    Next
    INDEX
    Explanations

    named entities and numbers in sports, religious, and science contexts

    oai_token-act-pair · gemini-2.0-flash

    Part of name, sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    GOTREF
    -0.75
     getItemId
    -0.69
     BoxFit
    -0.68
    tonsoft
    -0.65
    ellees
    -0.65
    writeFieldEnd
    -0.65
    reactstrap
    -0.61
     المعيارى
    -0.61
     mergeFrom
    -0.59
    HomeAsUpEnabled
    -0.59
    POSITIVE LOGITS
     otomatig
    0.58
     Италијани
    0.56
    IVENESS
    0.50
    amentals
    0.50
    esez
    0.49
    StoryboardSegue
    0.49
    ividual
    0.48
     @"";
    0.47
    ghts
    0.46
     Administrativna
    0.46
    Activations Density 11.308%

    No Known Activations