Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13415
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a singular or individual thing

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     itſelf
    -0.94
     Majefty
    -0.86
     Monfieur
    -0.84
     Efq
    -0.83
     ſeveral
    -0.80
     pleaſure
    -0.80
     myſelf
    -0.79
    DebuggerNonUser
    -0.75
     Jefus
    -0.75
     himſelf
    -0.73
    POSITIVE LOGITS
     single
    0.72
    single
    0.64
    Single
    0.60
     Single
    0.60
     M
    0.54
    sole
    0.54
     SINGLE
    0.53
    SINGLE
    0.51
    单
    0.49
     B
    0.48
    Activations Density 1.921%

    No Known Activations