© 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. 8581
    Prev
    Next
    INDEX
    Explanations

    somewhat arbitrary grouping of arrangements, technical words ending in "ant," some version of URL, and something to do with Facebook

    oai_token-act-pair · gemini-2.0-flash

    arrangements

    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
     Com
    -2.28
     Comp
    -2.19
     comp
    -2.13
    Com
    -2.11
     COM
    -2.08
    Comp
    -2.05
     com
    -2.00
     Kom
    -2.00
    COM
    -1.98
     kom
    -1.89
    POSITIVE LOGITS
    ItemBackground
    0.50
    LookAnd
    0.43
     singola
    0.43
    vgili
    0.42
    Rüyada
    0.41
    giau
    0.40
    expandindo
    0.39
     lettore
    0.39
    WithIOException
    0.39
    contentLoaded
    0.38
    Activations Density 1.323%

    No Known Activations