© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9743
    Prev
    Next
    INDEX
    Explanations

    descriptions of something continuing to be something

    oai_token-act-pair · gemini-2.0-flash

    be/have verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tvguidetime
    -1.11
     EconPapers
    -0.88
    хьтан
    -0.84
    Cyfeiriadau
    -0.84
    posedge
    -0.82
    :✨
    -0.81
     resourceCulture
    -0.80
    Personendaten
    -0.79
     الرياضيه
    -0.79
    期刊论文
    -0.77
    POSITIVE LOGITS
    ďaka
    0.52
     enää
    0.48
     future
    0.47
     now
    0.46
     futuras
    0.45
     tarko
    0.45
    future
    0.44
     suivantes
    0.44
     epä
    0.42
     prochaines
    0.42
    Activations Density 0.079%

    No Known Activations