© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6057
    Prev
    Next
    INDEX
    Explanations

    words related to activities, especially those that end in '-ing'.

    oai_token-act-pair · gemini-2.0-flash

    actions

    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
    s
    -0.79
    e
    -0.73
    el
    -0.59
    eu
    -0.59
    E
    -0.56
    ade
    -0.56
    schen
    -0.56
    z
    -0.56
    c
    -0.55
    es
    -0.55
    POSITIVE LOGITS
    ParallelGroup
    0.81
    moiselle
    0.66
     nôtre
    0.63
    cipais
    0.62
     noqa
    0.62
     charité
    0.61
     الحره
    0.61
     '\\;'
    0.60
     the
    0.59
     متحده
    0.59
    Activations Density 15.239%

    No Known Activations