© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5680
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the", often preceded by other short words

    oai_token-act-pair · gemini-2.0-flash

    plural nouns or general concepts

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AndEndTag
    -0.71
    },[])
    -0.64
    $'
    -0.62
    TestingModule
    -0.61
     Wikimedijinoj
    -0.60
     تعدى
    -0.57
     createContext
    -0.56
    <?
    -0.56
     Juifs
    -0.56
     endfor
    -0.56
    POSITIVE LOGITS
     laws
    0.59
     things
    0.57
     cases
    0.55
     examples
    0.53
     activities
    0.53
     ways
    0.53
     programs
    0.53
     strategies
    0.52
     factors
    0.52
     accounts
    0.52
    Activations Density 4.011%

    No Known Activations