© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13262
    Prev
    Next
    INDEX
    Explanations

    words with the substrings "as", "org", "art", "dia", "hemis", "mis", "diagno", or "fantas"

    oai_token-act-pair · gemini-2.0-flash

    technical / medical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    sial
    -0.74
    sia
    -0.73
    si
    -0.73
    siu
    -0.73
    sii
    -0.69
    sez
    -0.68
    SL
    -0.68
    sities
    -0.68
    se
    -0.65
    sir
    -0.65
    POSITIVE LOGITS
    Koordinaten
    0.45
    lccn
    0.44
    RTEE
    0.43
     gambe
    0.43
    Personensuche
    0.43
    InputBorder
    0.42
    ไง
    0.42
    Personendaten
    0.41
    הערות
    0.41
    windowFixed
    0.41
    Activations Density 1.852%

    No Known Activations