© 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. 1168
    Prev
    Next
    INDEX
    Explanations

    words related to storage capacity

    oai_token-act-pair · gemini-2.0-flash

    data and memory storage

    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
     storage
    -2.67
     Storage
    -2.56
    storage
    -2.44
    Storage
    -2.42
     STORAGE
    -2.41
     storing
    -2.23
    STORAGE
    -2.19
     stored
    -2.14
     Storing
    -1.95
     Stored
    -1.92
    POSITIVE LOGITS
     ticket
    0.57
     tickets
    0.55
     Tickets
    0.52
    ticket
    0.50
    IntoConstraints
    0.48
     Ticket
    0.48
     TICKETS
    0.48
    TICKETS
    0.48
    jface
    0.48
    cshtml
    0.48
    Activations Density 2.053%

    No Known Activations