© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10358
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly '19', '20', and '21' appearing at the beginning of lines or as list items

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    rd
    -1.32
    RD
    -1.02
     rd
    -0.93
     RD
    -0.85
    rds
    -0.84
    orteur
    -0.73
    Personendaten
    -0.72
    rdi
    -0.71
    EndInit
    -0.70
    MessageTagHelper
    -0.69
    POSITIVE LOGITS
    st
    0.98
     st
    0.77
    ST
    0.73
     ST
    0.63
     St
    0.60
    St
    0.60
    stow
    0.58
    stc
    0.55
     sti
    0.54
    stum
    0.52
    Activations Density 1.398%

    No Known Activations