© 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. 853
    Prev
    Next
    INDEX
    Explanations

    text related to docker commands and configuration

    oai_token-act-pair · gemini-2.0-flash

    software development

    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
     Administrativna
    -0.71
    енча
    -0.64
    elemField
    -0.60
    richTextPanel
    -0.60
     utafitiHapana
    -0.58
    styleType
    -0.56
    ViewImports
    -0.56
    homonymie
    -0.56
    principalColumn
    -0.56
    Milit
    -0.56
    POSITIVE LOGITS
    paraíso
    0.48
    dieron
    0.48
    ämmer
    0.47
    attendre
    0.47
     registrada
    0.45
     Kraken
    0.44
    BuildContext
    0.43
     tqdm
    0.42
     brownie
    0.41
     otel
    0.41
    Activations Density 8.683%

    No Known Activations