© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8329
    Prev
    Next
    INDEX
    Explanations

    words denoting frustration with a product either breaking or tangling.

    oai_token-act-pair · gemini-2.0-flash

    tangling/damage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     propOrder
    -0.60
     phylogeny
    -0.57
     toArray
    -0.55
     Efq
    -0.54
    cestry
    -0.54
    CROSSTALK
    -0.54
     deltaTime
    -0.53
    Ế
    -0.52
    UnsafeEnabled
    -0.52
     consuls
    -0.52
    POSITIVE LOGITS
    contentLoaded
    0.63
     виправивши
    0.61
     Ause
    0.59
     ?>/
    0.57
    DoubleQuotes
    0.53
     насељу
    0.53
    AnimationsModule
    0.52
     lenker
    0.47
    rfloor
    0.47
     Wide
    0.46
    Activations Density 1.664%

    No Known Activations