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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3018
    Prev
    Next
    INDEX
    Explanations

    the first few tokens in snippets of text describing some invention or process

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    脚注の使い方
    -0.97
     utafitiHapana
    -0.97
    ⓧ
    -0.84
    #+#
    -0.84
     متعلقه
    -0.78
    ViewInit
    -0.77
     CreateTagHelper
    -0.77
    TagMode
    -0.75
    parsedMessage
    -0.75
    RegistryLite
    -0.74
    POSITIVE LOGITS
    <bos>
    0.85
    '
    0.53
     thế
    0.43
    ’
    0.42
     for
    0.41
     key
    0.41
     complete
    0.41
     to
    0.40
    ast
    0.39
     إس
    0.39
    Activations Density 0.523%

    No Known Activations