© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3101
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases starting with the word "out."

    oai_token-act-pair · gemini-2.0-flash

    out

    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
    Personendaten
    -0.61
    Portály
    -0.59
     оригіналу
    -0.51
     članak
    -0.50
    bkz
    -0.50
    unknownFields
    -0.48
    offsetof
    -0.47
    jeta
    -0.46
    UEL
    -0.46
    ulfon
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    +#+#
    0.56
     IndexPath
    0.56
     Wartawan
    0.50
     متعلقه
    0.49
     eût
    0.49
    whats
    0.49
    erweise
    0.48
    tyfik
    0.48
    ForRow
    0.48
    Activations Density 0.436%

    No Known Activations