© 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. 13097
    Prev
    Next
    INDEX
    Explanations

    strings representing citations within academic papers

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act · 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
    <bos>
    -0.83
    Попис
    -0.71
     المعيارى
    -0.69
     purpoſe
    -0.69
     Italijani
    -0.66
    ituary
    -0.64
     uſe
    -0.63
     ſtate
    -0.63
     itſelf
    -0.63
     himo
    -0.62
    POSITIVE LOGITS
    Revenir
    0.59
    mögens
    0.46
     onCreateView
    0.44
    égek
    0.43
    EndContext
    0.43
    WriteLiteral
    0.43
    mml
    0.43
    viewDidLoad
    0.42
    setAccessible
    0.42
    ported
    0.42
    Activations Density 1.627%

    No Known Activations