© 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. 6147
    Prev
    Next
    INDEX
    Explanations

    the lowercase letter 'r' followed by a number or punctuation

    oai_token-act-pair · gemini-2.0-flash

    tokens related to the letter 'r'

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

    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_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
     random
    -0.60
     ra
    -0.50
     much
    -0.49
     Q
    -0.46
     q
    -0.45
    WEBPACK
    -0.44
     Burk
    -0.42
     He
    -0.42
     p
    -0.42
    ését
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    0.77
     صوتيه
    0.73
     ligiloj
    0.72
     Jefus
    0.66
    __":
    0.65
     myſelf
    0.65
    ыгана
    0.65
     viewDidLoad
    0.65
     Antar
    0.64
    StructEnd
    0.64
    Activations Density 1.001%

    No Known Activations