© 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. 4102
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words, potentially related to either lists, tests, or the word "or"

    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
     two
    -2.81
    Two
    -2.72
    two
    -2.66
     Two
    -2.61
     deux
    -2.31
    TWO
    -2.31
     TWO
    -2.27
     zwei
    -2.06
     three
    -1.92
     δύο
    -1.89
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    ########.
    0.53
    WriteAttribute
    0.53
     tenth
    0.51
    存于互联网档案馆
    0.49
    ofType
    0.49
    تقاوى
    0.48
    xiii
    0.48
     nth
    0.47
    èlement
    0.47
    Activations Density 7.652%

    No Known Activations