© 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. 1214
    Prev
    Next
    INDEX
    Explanations

    numbers and words associated with numbers

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    Two
    -1.33
    two
    -1.26
     Two
    -1.25
    TWO
    -1.19
     two
    -1.16
     TWO
    -1.05
    tw
    -0.98
    二
    -0.95
    Zwei
    -0.95
     tw
    -0.94
    POSITIVE LOGITS
     createState
    0.63
    yntaxException
    0.62
     Exactos
    0.61
     snippetHide
    0.60
     متعلقه
    0.58
     resourceCulture
    0.57
     cherchés
    0.56
    Бахар
    0.54
    WebElementEntity
    0.54
     Efq
    0.52
    Activations Density 5.688%

    No Known Activations