© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7328
    Prev
    Next
    INDEX
    Explanations

    words related to importance, priority and order

    oai_token-act-pair · gemini-2.0-flash

    technical documentation/specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     prior
    -3.23
    Prior
    -3.03
     Prior
    -3.03
    prior
    -2.97
     PRIOR
    -2.63
    PRIOR
    -2.14
     priors
    -1.56
     previous
    -0.95
     previo
    -0.90
     priori
    -0.89
    POSITIVE LOGITS
    EventListener
    0.51
    QualifiedName
    0.47
    InMillis
    0.47
    ◢
    0.46
    SEMICOLON
    0.42
    ombre
    0.42
    δες
    0.41
    onPress
    0.40
     yarar
    0.40
     Winslow
    0.40
    Activations Density 29.130%

    No Known Activations