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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9561
    Prev
    Next
    INDEX
    Explanations

    words related to food and dining

    oai_token-act-pair · gemini-2.0-flash

    meat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AutoresizingMask
    -0.63
    StructEnd
    -0.55
    ifflin
    -0.51
     ویکی‌آمباردا
    -0.49
    CppCodeGen
    -0.48
    asun
    -0.47
     мѣ
    -0.46
     vilja
    -0.46
     актив
    -0.46
    rungsseite
    -0.45
    POSITIVE LOGITS
     SwitchCompat
    0.65
    InjectAttribute
    0.65
     &___
    0.60
     незавершена
    0.59
     conf
    0.58
    ⓧ
    0.57
    UnusedPrivate
    0.53
    lego
    0.53
     Monza
    0.53
     tire
    0.51
    Activations Density 1.799%

    No Known Activations