© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11907
    Prev
    Next
    INDEX
    Explanations

    various types of punctuation marks, particularly those used in programming, math, or question/answer contexts

    oai_token-act-pair · gemini-2.0-flash

    phrases starting with 'This', 'It', 'They', 'The', or similar

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

    punctuation

    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
     Efq
    -0.58
     Majefty
    -0.55
    )|^{
    -0.54
    Réponse
    -0.53
     photolibrary
    -0.52
     ♂
    -0.51
     anchor
    -0.51
     Técnica
    -0.51
     Bohemian
    -0.49
     Púb
    -0.48
    POSITIVE LOGITS
     This
    1.31
     It
    1.23
     They
    1.20
     The
    1.14
     These
    1.09
     There
    1.08
     If
    1.05
     We
    1.03
     Each
    1.02
     Some
    0.93
    Activations Density 4.540%

    No Known Activations