© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3400
    Prev
    Next
    INDEX
    Explanations

    instances of advancement or movement of an abstract or concrete noun.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'pass'

    np_token-act-pair-logits · gpt-4o-mini

    pass

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     createState
    -0.96
    참고
    -0.76
    intios
    -0.69
    Datuak
    -0.66
     MainAxisSize
    -0.65
    initComponents
    -0.64
    QMetaType
    -0.64
    makeConstraints
    -0.63
    AnchorStyles
    -0.63
    brainly
    -0.62
    POSITIVE LOGITS
     pass
    1.54
     passed
    1.49
     passing
    1.40
     past
    1.34
     Pass
    1.26
    pass
    1.24
    passed
    1.24
    Passing
    1.23
     Passing
    1.20
    Pass
    1.19
    Activations Density 1.229%

    No Known Activations