© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    mostly grammatical structures, especially determiners and prepositions close to nouns, often in technical documents

    oai_token-act-pair · gemini-2.0-flash

    say "basis"

    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
     base
    -2.88
     Base
    -2.84
    base
    -2.70
     bases
    -2.66
    Base
    -2.59
     Bases
    -2.55
     BASE
    -2.42
    BASE
    -2.41
     Basis
    -2.36
    bases
    -2.31
    POSITIVE LOGITS
    marshaller
    0.43
    SNMP
    0.39
     SNR
    0.39
    upné
    0.38
    uro
    0.38
    SNR
    0.37
    kheim
    0.36
    schuhe
    0.35
    外部链接
    0.35
     marrone
    0.35
    Activations Density 2.520%

    No Known Activations