© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14893
    Prev
    Next
    INDEX
    Explanations

    the word "up" preceded or followed by directional or temporal words

    oai_token-act-pair · gemini-2.0-flash

    up

    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
     للمعارف
    -0.74
    UnusedPrivate
    -0.67
    eeeeeeee
    -0.65
    eer
    -0.65
    of
    -0.59
    zação
    -0.59
    ee
    -0.58
     Baillargeon
    -0.58
    eee
    -0.58
    InputBorder
    -0.57
    POSITIVE LOGITS
    setting
    0.55
    state
    0.52
    turned
    0.52
    thâu
    0.49
    amaño
    0.48
    shot
    0.48
    sumoto
    0.47
     McLean
    0.47
    set
    0.47
    CppMethod
    0.46
    Activations Density 20.765%

    No Known Activations