© 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. 10412
    Prev
    Next
    INDEX
    Explanations

    code snippets and first-person and second-person pronouns with "can"

    oai_token-act-pair · 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
    '
    -0.81
    ’
    -0.76
    TagHelpers
    -0.65
     worth
    -0.55
    ‘
    -0.55
    (${
    -0.50
    Worth
    -0.50
     ${
    -0.50
     Worth
    -0.49
    ……
    -0.47
    POSITIVE LOGITS
     s
    1.82
     t
    0.91
     ll
    0.79
    قایناق‌لار
    0.78
     m
    0.77
    Tikang
    0.71
    Poloha
    0.70
    檚
    0.66
     SwitchCompat
    0.65
    PostExecute
    0.63
    Activations Density 1.028%

    No Known Activations