© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6235
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to scientific studies or experimental setups.

    oai_token-act-pair · gemini-2.0-flash

    scientific proposals and asymmetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.68
    <eos>
    -0.46
    ferrer
    -0.46
    ↵
    -0.46
    chle
    -0.45
    </em>
    -0.44
    τεύ
    -0.43
     helyez
    -0.43
     more
    -0.42
    ชั่น
    -0.41
    POSITIVE LOGITS
    المناصب
    1.10
     للمعارف
    1.09
     kasarigan
    1.02
    RectangleBorder
    0.96
     CreateTagHelper
    0.90
    DataAnnotations
    0.90
    adaptiveStyles
    0.89
    tagHelperRunner
    0.85
    Composable
    0.84
     GenerationType
    0.84
    Activations Density 4.507%

    No Known Activations