© 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. 11854
    Prev
    Next
    INDEX
    Explanations

    the words "on," "our," "my," "their," "this," and "the" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    say "way"

    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
     EClass
    -1.07
     الرياضيه
    -0.92
     NUKAT
    -0.91
    __(/*!
    -0.88
    ScopeManager
    -0.88
    +#+
    -0.86
    ISupport
    -0.86
     fidé
    -0.85
     تضيفلها
    -0.84
    NamedQuery
    -0.84
    POSITIVE LOGITS
     I
    0.48
     you
    0.47
     was
    0.43
     to
    0.38
     it
    0.37
     Place
    0.36
     the
    0.34
    "
    0.34
     (
    0.34
    expects
    0.33
    Activations Density 3.887%

    No Known Activations