© 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. 6619
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly arbitrary bit of code, numbers, and symbols

    oai_token-act-pair · gemini-2.0-flash

    number 6

    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
     createContext
    -0.84
     defaultstate
    -0.74
    ThroughAttribute
    -0.68
     Paglinawan
    -0.63
    цездатний
    -0.61
    ItemBackground
    -0.60
    AndEndTag
    -0.60
    enumi
    -0.57
     CreateTagHelper
    -0.56
    oredCriteria
    -0.56
    POSITIVE LOGITS
    6
    1.58
     six
    1.24
     sixth
    1.12
     Six
    1.09
     Sixth
    1.03
     sechs
    1.03
     seis
    1.01
    ６
    0.99
     SIX
    0.92
     шесть
    0.92
    Activations Density 4.498%

    No Known Activations