© 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. 1206
    Prev
    Next
    INDEX
    Explanations

    instances of the word "The" or "the" at the beginning of a sentence

    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
    ViewFeatures
    -0.91
     виправивши
    -0.90
     createContext
    -0.85
    abestanden
    -0.83
    GEBURTSDATUM
    -0.81
    tvguidetime
    -0.80
    Vidite
    -0.77
     مشين
    -0.76
    
    -0.75
     bezeichneter
    -0.71
    POSITIVE LOGITS
     U
    0.54
     Holy
    0.47
     Solid
    0.46
     Virgin
    0.45
     uy
    0.45
    arabe
    0.45
    cal
    0.44
    EOUS
    0.44
     Nazionale
    0.44
    kN
    0.43
    Activations Density 1.667%

    No Known Activations