© 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. 10217
    Prev
    Next
    INDEX
    Explanations

    words related to advice, warnings, limitations, and things to be careful about

    oai_token-act-pair · gemini-2.0-flash

    Caution/deference

    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
     nahilalakip
    -0.68
    AddTagHelper
    -0.57
    észetes
    -0.56
     CommonModule
    -0.55
    iteritems
    -0.53
    Aholisi
    -0.52
     CascadeType
    -0.52
    _));
    -0.51
    SizeF
    -0.51
    setVerticalGroup
    -0.51
    POSITIVE LOGITS
     significant
    0.55
    MethodManager
    0.51
      (
    0.48
    PLANATION
    0.48
    inheritDoc
    0.48
    неопр
    0.47
    significant
    0.46
    quiti
    0.46
    +#+
    0.45
    giti
    0.45
    Activations Density 6.543%

    No Known Activations