© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12316
    Prev
    Next
    INDEX
    Explanations

    words containing the "hydro" prefix, often in a chemistry context

    oai_token-act-pair · gemini-2.0-flash

    terms related to hydro-related concepts

    np_token-act-pair-logits · gpt-4o-mini

    hydro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    NameInMap
    -0.63
    XmlAccessType
    -0.55
    psia
    -0.47
    ltä
    -0.46
     vastaan
    -0.46
    tioners
    -0.46
    iteurs
    -0.45
     Irvin
    -0.45
    itri
    -0.45
    Viva
    -0.44
    POSITIVE LOGITS
    فایل‌لار
    0.53
    jsxFileName
    0.49
    SPATH
    0.49
    FORMS
    0.49
     Grünen
    0.48
    gway
    0.48
     Baillargeon
    0.48
    newtheorem
    0.47
     mellitus
    0.47
    ulgação
    0.47
    Activations Density 0.860%

    No Known Activations