© 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. 10408
    Prev
    Next
    INDEX
    Explanations

    abstract nouns related to the state of affairs or qualities such as relentless, obvious, formal, true, humanity, death, potential

    oai_token-act-pair · gemini-2.0-flash

    underlying truths

    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
    .
    -0.62
    P
    -0.50
    e
    -0.49
     P
    -0.47
     
    -0.47
    a
    -0.46
     véritables
    -0.45
    A
    -0.44
    E
    -0.43
    C
    -0.42
    POSITIVE LOGITS
     Majefty
    1.32
     purpoſe
    1.30
     itſelf
    1.26
     ModelExpression
    1.25
     Monfieur
    1.23
     pleaſure
    1.21
    neſs
    1.21
     themſelves
    1.20
     myſelf
    1.20
    ſelf
    1.19
    Activations Density 11.922%

    No Known Activations