© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6869
    Prev
    Next
    INDEX
    Explanations

    text related to typography and fonts

    oai_token-act-pair · gemini-2.0-flash

    say "letters"

    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
     letter
    -2.48
     letters
    -2.42
     Letter
    -2.41
     Letters
    -2.38
    Letter
    -2.34
    letter
    -2.28
     LETTER
    -2.28
     LETTERS
    -2.23
    LETTER
    -2.23
    letters
    -2.23
    POSITIVE LOGITS
    Демографія
    0.60
    setVerticalGroup
    0.44
     let
    0.43
    quez
    0.41
     &$
    0.40
    JpaRepository
    0.39
     Preis
    0.37
    بوابة
    0.36
     Let
    0.36
    Let
    0.36
    Activations Density 1.082%

    No Known Activations