© 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. 6674
    Prev
    Next
    INDEX
    Explanations

    words related to government programs and initiatives

    oai_token-act-pair · gemini-2.0-flash

    planned undertakings

    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
     aimed
    -0.95
     aiming
    -0.77
     geared
    -0.75
     Directed
    -0.70
     directed
    -0.69
     aims
    -0.67
     focused
    -0.66
    directed
    -0.65
     bertujuan
    -0.63
     targeted
    -0.62
    POSITIVE LOGITS
     referenties
    0.69
    GEBURTSDATUM
    0.65
    findpost
    0.58
    GOTREF
    0.56
     hauts
    0.52
     nakalista
    0.51
     للمعارف
    0.50
    ỡng
    0.50
     مشين
    0.47
    AsUp
    0.47
    Activations Density 25.300%

    No Known Activations