© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9532
    Prev
    Next
    INDEX
    Explanations

    spaces and characters used to delimit data in tables and forms

    oai_token-act-pair · gemini-2.0-flash

    scientific data and code

    np_max-act · gemini-2.0-flash

    leading space

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    sizeCache
    -0.91
     ExecuteAsync
    -0.88
     CreateTagHelper
    -0.80
    UnusedPrivate
    -0.76
    AccessorTable
    -0.74
    +#+#
    -0.72
     OMITBAD
    -0.69
     oleo
    -0.64
     SqlCommand
    -0.63
     дописавши
    -0.63
    POSITIVE LOGITS
    <bos>
    1.19
    ’
    0.54
    '
    0.54
    헌
    0.53
    '||
    0.52
     
    0.50
     soi
    0.47
    soort
    0.47
     on
    0.46
     La
    0.46
    Activations Density 2.205%

    No Known Activations