© 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. 8524
    Prev
    Next
    INDEX
    Explanations

    words related to the success or failure of an activity

    oai_token-act-pair · gemini-2.0-flash

    Obscure words

    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
    SequentialGroup
    -0.61
    DrawerToggle
    -0.59
     whit
    -0.56
    SourceChecksum
    -0.51
    megap
    -0.47
     Wiktionnaire
    -0.47
    intellij
    -0.46
    prnewswire
    -0.45
    addCriterion
    -0.45
     Eocene
    -0.45
    POSITIVE LOGITS
     CYTHON
    0.69
    StoryboardSegue
    0.63
    Bril
    0.58
    isio
    0.57
    клопе
    0.56
    jara
    0.55
     mo
    0.53
     apar
    0.51
     ø
    0.51
    mö
    0.51
    Activations Density 6.028%

    No Known Activations