© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10690
    Prev
    Next
    INDEX
    Explanations

    the word "expected" and sometimes the word "usual"

    oai_token-act-pair · gemini-2.0-flash

    expected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     disponibilités
    -0.75
    FTFY
    -0.71
    \{\\
    -0.67
     يتيمه
    -0.66
    رشف
    -0.65
    StateChange
    -0.64
    noz
    -0.63
    tahankan
    -0.63
    χή
    -0.62
     barat
    -0.62
    POSITIVE LOGITS
     useNavigate
    0.68
     useDispatch
    0.59
    NameValuePair
    0.56
     sympy
    0.56
     ""],
    0.53
    epam
    0.51
     combineReducers
    0.50
    Leod
    0.50
    OkHttpClient
    0.50
    جغرافيا
    0.49
    Activations Density 0.484%

    No Known Activations