© 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. 11467
    Prev
    Next
    INDEX
    Explanations

    instances of "if you" and related conditional clauses

    oai_token-act-pair · gemini-2.0-flash

    conditional phrases

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

    If

    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
    ChildScrollView
    -0.50
    IF
    -0.44
    if
    -0.44
     if
    -0.43
     IF
    -0.43
     verz
    -0.42
     lan
    -0.42
     lag
    -0.42
     saws
    -0.42
    zd
    -0.41
    POSITIVE LOGITS
     myſelf
    0.90
     themſelves
    0.83
     reaſon
    0.81
     purpoſe
    0.79
     houſe
    0.77
     raiſ
    0.76
    ValueStyle
    0.74
     Monfieur
    0.73
    Personensuche
    0.73
     pleaſure
    0.72
    Activations Density 0.712%

    No Known Activations