© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    code related to locating a view

    oai_token-act-pair · gemini-2.0-flash

    code related to views

    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
    GEBURTSDATUM
    -0.72
    <bos>
    -0.59
    enterOuterAlt
    -0.51
    ArrowToggle
    -0.49
    تقاوى
    -0.47
    NameInMap
    -0.44
    __':
    -0.43
    transQ
    -0.43
    resave
    -0.43
     positively
    -0.43
    POSITIVE LOGITS
     suivante
    0.68
     précédents
    0.64
     traités
    0.64
     vieilles
    0.63
    Externé
    0.59
     précédentes
    0.59
     actuels
    0.59
     suivants
    0.59
    deles
    0.57
    ScopeManager
    0.57
    Activations Density 6.245%

    No Known Activations