© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific writing in LaTeX

    oai_token-act-pair · gemini-2.0-flash

    words related to mathematical expressions and relationships

    np_token-act-pair-logits · gpt-4o-mini

    mathematical expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     g
    -0.62
     Z
    -0.60
     (
    -0.58
     O
    -0.55
     di
    -0.52
     p
    -0.52
     x
    -0.52
    sin
    -0.52
     n
    -0.51
     L
    -0.51
    POSITIVE LOGITS
     pleaſure
    0.92
     myſelf
    0.88
     themſelves
    0.83
     ſeveral
    0.82
     purpoſe
    0.81
     becauſe
    0.80
    Jereo
    0.79
     ſever
    0.78
     himſelf
    0.76
    ########.
    0.76
    Activations Density 7.312%

    No Known Activations