© 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. 9604
    Prev
    Next
    INDEX
    Explanations

    lines containing only whitespace and a number

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or functions

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

    Java code

    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
    EditorBrowsable
    -0.65
    OGND
    -0.59
    makedirs
    -0.56
    endphp
    -0.55
     <<<<<<<<<<<<<<
    -0.55
    ::_('
    -0.54
    tonsoft
    -0.54
    edas
    -0.51
     Reverso
    -0.50
    Linq
    -0.49
    POSITIVE LOGITS
    InjectAttribute
    0.63
     الدولى
    0.58
    astéroïdes
    0.53
    SerializedSize
    0.49
    Referències
    0.48
     sanitaire
    0.48
    WithMany
    0.47
     Busse
    0.47
     Xp
    0.46
    beginTransaction
    0.46
    Activations Density 0.720%

    No Known Activations