© 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. 855
    Prev
    Next
    INDEX
    Explanations

    Java-style documentation strings

    oai_token-act-pair · gemini-2.0-flash

    *

    np_max-act · 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
    <bos>
    -1.58
    The
    -0.58
    '
    -0.57
    <
    -0.57
    1
    -0.54
    7
    -0.54
    2
    -0.53
    /*
    -0.53
    5
    -0.52
    M
    -0.50
    POSITIVE LOGITS
    HomeAsUpEnabled
    1.05
    NameInMap
    0.96
     snippetHide
    0.91
     Normdatei
    0.88
    aarrggbb
    0.87
     CreateTagHelper
    0.84
     beginnetje
    0.84
     EconPapers
    0.84
    ThroughAttribute
    0.84
    parsedMessage
    0.82
    Activations Density 0.931%

    No Known Activations