© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15824
    Prev
    Next
    INDEX
    Explanations

    text describing methods for manipulating physical objects, particularly wrapping things

    oai_token-act-pair · gemini-2.0-flash

    wrapped items

    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
     wrap
    -2.70
     wrapping
    -2.64
     Wrap
    -2.58
     wrapped
    -2.53
     wraps
    -2.48
     Wrapping
    -2.45
    Wrap
    -2.36
     Wrapped
    -2.33
    wrap
    -2.28
     WRAP
    -2.27
    POSITIVE LOGITS
    mybatisplus
    0.58
    IndentedString
    0.52
    PROMOTED
    0.51
    LookAnd
    0.50
     DBNull
    0.49
    ThroughAttribute
    0.48
    spesies
    0.47
    ruptedException
    0.47
    queryInterface
    0.46
    Void
    0.45
    Activations Density 2.396%

    No Known Activations