© 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. 8563
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded by words indicating location

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     resourceCulture
    -0.73
    awtextra
    -0.65
     مشين
    -0.62
    RegistryLite
    -0.61
     kaarangay
    -0.60
     فريبيس
    -0.56
    featureID
    -0.53
    UnusedPrivate
    -0.53
     esternos
    -0.52
    }))
    -0.49
    POSITIVE LOGITS
     middle
    2.31
    middle
    1.97
     MIDDLE
    1.48
    Middle
    1.30
    MIDDLE
    1.20
     Middle
    0.94
     middel
    0.94
     meio
    0.66
     midden
    0.57
     medio
    0.56
    Activations Density 2.252%

    No Known Activations