© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14726
    Prev
    Next
    INDEX
    Explanations

    the letter "L" appearing at the start of a word or a URL

    oai_token-act-pair · gemini-2.0-flash

    capital letter 'L' appearances

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

    L

    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
     bien
    -0.43
    ias
    -0.42
     L
    -0.41
    -
    -0.40
     (
    -0.38
     so
    -0.38
    !
    -0.37
     le
    -0.37
    <eos>
    -0.36
     об
    -0.36
    POSITIVE LOGITS
     itſelf
    0.90
     raiſ
    0.90
     ſtate
    0.89
     Monfieur
    0.88
     Efq
    0.88
     quæ
    0.87
     Reſ
    0.87
     pleaſure
    0.85
     >=",
    0.83
     myſelf
    0.83
    Activations Density 0.079%

    No Known Activations