© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 15267
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to mineralogy and geology, especially those describing the composition, formation, and properties of minerals

    oai_token-act-pair · gemini-2.0-flash

    geology and ores

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    хьтан
    -0.62
    ]")]
    -0.55
    .*")]
    -0.55
    $_['
    -0.53
    UrlResolution
    -0.53
    etcode
    -0.52
    FontOfSize
    -0.50
    )"),
    -0.50
    anglès
    -0.50
    DllImport
    -0.50
    POSITIVE LOGITS
     deuter
    0.50
     للاسماء
    0.45
    principalTable
    0.45
     onAnimation
    0.45
     bo
    0.45
    SequentialGroup
    0.44
     représ
    0.44
     peric
    0.43
     olor
    0.42
     Bo
    0.42
    Activations Density 10.236%

    No Known Activations