© 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. 10154
    Prev
    Next
    INDEX
    Explanations

    past-tense descriptions of situations, especially in sports

    oai_token-act-pair · gemini-2.0-flash

    was

    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
     qui
    -0.58
     الاجتما
    -0.57
    SourceChecksum
    -0.54
     prev
    -0.48
    BindView
    -0.48
    <eos>
    -0.47
     go
    -0.46
     base
    -0.44
     Go
    -0.44
     <<<<<<<<<<<<<<
    -0.44
    POSITIVE LOGITS
     uſed
    0.81
     myſelf
    0.76
     itſelf
    0.75
     Jefus
    0.71
     cdti
    0.70
     onBind
    0.68
     themſelves
    0.66
     himſelf
    0.65
    styleUrls
    0.64
     ―――――
    0.63
    Activations Density 0.651%

    No Known Activations