© 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. 14048
    Prev
    Next
    INDEX
    Explanations

    proper nouns and related inflections

    oai_token-act-pair · gemini-2.0-flash

    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_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
     as
    -0.43
     two
    -0.37
     and
    -0.34
     who
    -0.33
     i
    -0.33
     that
    -0.32
     for
    -0.32
     em
    -0.32
     can
    -0.32
     first
    -0.32
    POSITIVE LOGITS
     démocr
    0.99
     étoient
    0.98
     varandra
    0.91
     Normdatei
    0.90
     présidenti
    0.88
     avoient
    0.88
     découver
    0.85
     flesta
    0.84
     anún
    0.84
     élevées
    0.84
    Activations Density 7.436%

    No Known Activations