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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5981
    Prev
    Next
    INDEX
    Explanations

    code snippets with delimiters, likely related to memory addresses or data storage

    oai_token-act-pair · gemini-2.0-flash

    match

    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
     And
    -0.65
     Well
    -0.60
     Here
    -0.59
     Are
    -0.59
     So
    -0.59
     This
    -0.59
     Most
    -0.59
     Now
    -0.58
     We
    -0.57
     It
    -0.57
    POSITIVE LOGITS
     propOrder
    0.61
     purpoſe
    0.53
     Efq
    0.52
    IFORNIA
    0.52
     autorytatywna
    0.52
    loài
    0.51
     success
    0.51
     myſelf
    0.50
     behavior
    0.49
     release
    0.48
    Activations Density 34.633%

    No Known Activations