© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13807
    Prev
    Next
    INDEX
    Explanations

    words related to music, photography, business, and finance

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    хьтан
    -0.73
    ousand
    -0.69
    contentLoaded
    -0.65
    tling
    -0.62
    lyde
    -0.61
    splatz
    -0.60
    chromatic
    -0.60
     onCreateView
    -0.60
    Personendaten
    -0.59
    ctober
    -0.59
    POSITIVE LOGITS
    AxisAlignment
    0.57
    RegressionTest
    0.53
    tvguidetime
    0.47
     interesan
    0.47
    Kilder
    0.46
     GenerationType
    0.45
    dropIfExists
    0.44
    GOTREF
    0.44
    телни
    0.43
    ElementException
    0.43
    Activations Density 6.793%

    No Known Activations