© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    words related to memory management and computer architecture

    oai_token-act-pair · gemini-2.0-flash

    memory allocation

    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
     AssemblyCulture
    -0.98
     Мексичка
    -0.98
     Савезне
    -0.93
    WebServlet
    -0.84
    NameInMap
    -0.78
    LookAnd
    -0.75
    UrlResolution
    -0.75
    DialogContent
    -0.75
     ModelExpression
    -0.72
    ftagPool
    -0.72
    POSITIVE LOGITS
     backed
    0.45
     gap
    0.44
     scattered
    0.43
     poisoned
    0.41
     girdle
    0.40
     HUD
    0.40
    AZA
    0.40
     oblast
    0.40
    GAP
    0.40
     DEA
    0.40
    Activations Density 12.949%

    No Known Activations