© 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. 4579
    Prev
    Next
    INDEX
    Explanations

    it seems fairly confused, activating on phone contact details, fragments of the word "client" and some seemingly random numbers

    oai_token-act-pair · gemini-2.0-flash

    code or file paths

    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
     EK
    -1.14
     Ei
    -1.13
     EV
    -1.13
     EG
    -1.10
     ELE
    -1.10
     É
    -1.09
     EI
    -1.09
     EP
    -1.09
     EM
    -1.09
     Ele
    -1.09
    POSITIVE LOGITS
    InitVars
    0.62
    rungsseite
    0.58
    IsMutable
    0.57
    Geplaatst
    0.56
     nahilalakip
    0.53
    setViewportView
    0.48
    TagMode
    0.48
    PyExc
    0.46
    sidemargin
    0.46
    ofollow
    0.44
    Activations Density 1.107%

    No Known Activations