© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15310
    Prev
    Next
    INDEX
    Explanations

    what looks like it could be a small number of specific, short, non-English words.

    oai_token-act-pair · gemini-2.0-flash

    whe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    BeginInit
    -0.53
     Normdatei
    -0.48
    utia
    -0.48
    ichia
    -0.48
    rån
    -0.47
    InjectAttribute
    -0.47
    verwijspagina
    -0.45
     ácido
    -0.45
    IntoConstraints
    -0.44
    nt
    -0.43
    POSITIVE LOGITS
     ProtoMessage
    0.62
    Portály
    0.60
    المناصب
    0.59
    ens
    0.55
    emf
    0.55
    RepeatedField
    0.52
    Rhestr
    0.51
    drawSprites
    0.51
    esl
    0.51
    enz
    0.51
    Activations Density 0.856%

    No Known Activations