© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 826
    Prev
    Next
    INDEX
    Explanations

    the letter "r" at the start of words, particularly when that word has something to do with a computer or technology in general

    oai_token-act-pair · gemini-2.0-flash

    r

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AttributeSet
    -0.91
     Meksiku
    -0.74
     生命周期
    -0.68
     surla
    -0.67
    EDEFAULT
    -0.66
     مشين
    -0.65
     aikaa
    -0.64
    Filmographie
    -0.64
    MENAFN
    -0.63
     MaterialApp
    -0.63
    POSITIVE LOGITS
    rop
    0.44
     متعلقه
    0.44
    hal
    0.42
    logan
    0.42
    lg
    0.41
     AssemblyTitle
    0.40
    rane
    0.39
     four
    0.39
     ten
    0.39
    lr
    0.38
    Activations Density 2.255%

    No Known Activations