© 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. 12860
    Prev
    Next
    INDEX
    Explanations

    what appears to be noise, including names, numbers, and other seemingly random characters that may be misinterpretations of text

    oai_token-act-pair · gemini-2.0-flash

    Uncommon fragments of words

    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
    AddTagHelper
    -0.46
    よいよ
    -0.46
    üyor
    -0.46
     lap
    -0.43
    ródło
    -0.40
     heated
    -0.38
     ranks
    -0.38
     frequenza
    -0.38
    czeń
    -0.37
    さすがに
    -0.37
    POSITIVE LOGITS
     AssemblyTitle
    0.90
    DockStyle
    0.87
    rungsseite
    0.84
    
    0.77
    ConstraintMaker
    0.77
    GEBURTS
    0.76
    ContentAsync
    0.74
    StoryboardSegue
    0.73
    writeFieldEnd
    0.71
     &___
    0.63
    Activations Density 18.284%

    No Known Activations