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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10285
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    archaic or stylized text

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

    archaic/foreign words

    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
     
    -1.13
     d
    -1.07
     in
    -1.02
     b
    -1.02
     to
    -1.02
     p
    -1.02
     he
    -1.02
     du
    -1.00
     le
    -0.99
     di
    -0.99
    POSITIVE LOGITS
     itſelf
    2.28
     myſelf
    2.11
     Shakspeare
    2.02
     Jefus
    1.95
     pleaſure
    1.90
     Monfieur
    1.89
     Efq
    1.89
     ſeveral
    1.88
     Majefty
    1.85
     Diſ
    1.84
    Activations Density 4.497%

    No Known Activations