© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8685
    Prev
    Next
    INDEX
    Explanations

    the word "the" and other common grammatical words and phrases

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     myſelf
    -1.27
     Houſe
    -1.21
     houſe
    -1.18
     Majefty
    -1.16
     ſeveral
    -1.13
     ་་
    -1.10
     itſelf
    -1.10
     ―――――
    -1.09
     Diſ
    -1.08
     pleaſure
    -1.04
    POSITIVE LOGITS
     l
    0.52
     an
    0.51
     par
    0.51
     a
    0.50
     r
    0.48
     the
    0.47
     d
    0.47
     van
    0.46
     back
    0.46
     
    0.44
    Activations Density 2.857%

    No Known Activations