© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13131
    Prev
    Next
    INDEX
    Explanations

    the word "and", sometimes in sequence or conjunction with other words

    oai_token-act-pair · gemini-2.0-flash

    and

    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
     voegen
    -0.44
    inerja
    -0.43
    çı
    -0.40
    Load
    -0.40
    osin
    -0.40
    same
    -0.40
    hå
    -0.40
    大
    -0.39
    Clap
    -0.39
     Brasileiro
    -0.39
    POSITIVE LOGITS
    OGND
    0.86
     الحره
    0.82
    bootstrapcdn
    0.81
    expandindo
    0.80
     utafitiHapana
    0.80
    WebServlet
    0.79
    Viited
    0.78
    tvguidetime
    0.75
     للمعارف
    0.73
     itſelf
    0.73
    Activations Density 1.623%

    No Known Activations