© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    language and notation common in mathematical proofs

    oai_token-act-pair · gemini-2.0-flash

    case

    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
     sarili
    -0.52
    DeleteBehavior
    -0.49
    ory
    -0.49
    zzleHttp
    -0.48
     Bajos
    -0.47
    ুল
    -0.45
     itself
    -0.44
     sine
    -0.44
     against
    -0.43
     Για
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.87
     nakalista
    0.73
     /\.
    0.69
     mxArray
    0.67
    complexType
    0.65
    oneofs
    0.62
    toMatchSnapshot
    0.62
     يتيمه
    0.61
     jsPsych
    0.60
    ########.
    0.60
    Activations Density 29.566%

    No Known Activations