© 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. 9198
    Prev
    Next
    INDEX
    Explanations

    danish words

    oai_token-act-pair · 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
    argate
    -0.47
    etsen
    -0.45
    ciech
    -0.45
    ledem
    -0.44
    onshire
    -0.43
     dalamnya
    -0.42
    ffilm
    -0.42
    bourhood
    -0.42
    tanooga
    -0.41
     Pingback
    -0.41
    POSITIVE LOGITS
    Identyfik
    0.71
     HasFactory
    0.70
     ivelany
    0.66
     lateinit
    0.65
    expandindo
    0.63
    onAttach
    0.61
    CodeAttribute
    0.61
    NameInMap
    0.60
    ########.
    0.59
     protoimpl
    0.58
    Activations Density 0.402%

    No Known Activations