© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10553
    Prev
    Next
    INDEX
    Explanations

    phrases with commas and words that indicate comparison, liking, or attraction

    oai_token-act-pair · gemini-2.0-flash

    say the

    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
     the
    -1.35
     Majefty
    -1.30
     myſelf
    -1.29
     Reſ
    -1.27
     Jefus
    -1.24
     Monfieur
    -1.23
     Houſe
    -1.21
     ſtate
    -1.21
     purpoſe
    -1.21
     itſelf
    -1.19
    POSITIVE LOGITS
     O
    0.63
     (
    0.61
    <eos>
    0.60
     i
    0.59
     T
    0.58
    ↵
    0.56
     M
    0.56
     
    0.55
    ↵↵
    0.55
     e
    0.54
    Activations Density 0.384%

    No Known Activations