© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1291
    Prev
    Next
    INDEX
    Explanations

    numbers and expressions of quantity

    oai_token-act-pair · gemini-2.0-flash

    The number 1

    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
    SourceChecksum
    -0.71
    InjectAttribute
    -0.68
     يتيمه
    -0.63
    RenderAtEndOf
    -0.63
     незавершена
    -0.56
     kaarangay
    -0.56
    Personendaten
    -0.54
     >=",
    -0.54
    хьтан
    -0.54
    WebElementEntity
    -0.53
    POSITIVE LOGITS
    1
    2.27
     ১
    1.09
    1
    1.09
    ১
    0.91
     १
    0.90
     fifteenth
    0.85
     sixteenth
    0.84
     ١
    0.80
     fourteenth
    0.78
     thirteenth
    0.77
    Activations Density 5.020%

    No Known Activations