© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6704
    Prev
    Next
    INDEX
    Explanations

    equal signs and array/object accessors adjacent to certain keywords used in programming languages

    oai_token-act-pair · gemini-2.0-flash

    equals sign

    np_max-act · gemini-2.0-flash

    equals sign

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     =
    -1.75
     $=$
    -1.33
     $=
    -1.25
     $=\
    -1.18
     =$
    -1.09
     =",
    -1.09
     ='
    -1.06
     }=\
    -1.06
    =+
    -1.05
    ＝
    -1.02
    POSITIVE LOGITS
    .
    0.75
      
    0.73
     and
    0.69
    ↵↵
    0.69
    ,
    0.66
    <b>
    0.65
    '
    0.65
     the
    0.63
    </b>
    0.62
    </i>
    0.61
    Activations Density 1.521%

    No Known Activations