© 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. 6192
    Prev
    Next
    INDEX
    Explanations

    code snippets containing the word "expect"

    oai_token-act-pair · gemini-2.0-flash

    programming terms or expressions

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

    code/debugging

    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
    writeFieldEnd
    -0.92
     שוליים
    -0.90
     BoxFit
    -0.88
    ]")]
    -0.84
     '\\;'
    -0.81
    BeginContext
    -0.80
     unknownFields
    -0.79
     kaynağından
    -0.78
     насељу
    -0.75
    parsedMessage
    -0.75
    POSITIVE LOGITS
     fasse
    0.51
    Sprintf
    0.50
     virke
    0.48
     going
    0.47
     flamme
    0.45
    leggen
    0.44
    verket
    0.43
     <
    0.43
    ><
    0.43
     offers
    0.43
    Activations Density 7.868%

    No Known Activations