© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 987
    Prev
    Next
    INDEX
    Explanations

    words in all caps, and legal/technical jargon.

    oai_token-act-pair · gemini-2.0-flash

    Academic/technical text

    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
    ftant
    -0.69
    iffion
    -0.69
    iffance
    -0.66
    uſe
    -0.65
    tiérrez
    -0.65
    ſſer
    -0.64
    virons
    -0.64
    ratulations
    -0.63
    liſh
    -0.61
    ipheral
    -0.60
    POSITIVE LOGITS
    kloped
    0.43
    ks
    0.40
    tomans
    0.36
    li
    0.35
    izability
    0.35
    us
    0.35
    thodoxy
    0.34
    llywood
    0.34
    ck
    0.34
    thodon
    0.34
    Activations Density 5.743%

    No Known Activations