© 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. 10189
    Prev
    Next
    INDEX
    Explanations

    Java code

    oai_token-act-pair · gemini-2.0-flash

    say "set word"

    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
     gets
    -0.83
     Get
    -0.81
     gotten
    -0.80
     getting
    -0.77
     Gets
    -0.73
     get
    -0.72
     got
    -0.69
     Getting
    -0.67
     GET
    -0.66
    AndGet
    -0.65
    POSITIVE LOGITS
    set
    0.84
    Set
    0.75
     ſet
    0.74
     SET
    0.73
    setDo
    0.72
    SET
    0.70
     myſelf
    0.70
     sett
    0.69
     Anſ
    0.68
     ſche
    0.68
    Activations Density 5.579%

    No Known Activations