© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11760
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of rocks and minerals found in nature, and their usage

    oai_token-act-pair · gemini-2.0-flash

    Geology/mineralogy

    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
    kloped
    -0.63
    ensuremath
    -0.60
    dafx
    -0.57
    httphttps
    -0.57
    SerializedSize
    -0.54
    ThroughAttribute
    -0.54
    RegistryLite
    -0.52
    NavController
    -0.52
    InsertCommand
    -0.51
    +#+#
    -0.51
    POSITIVE LOGITS
    -------------</
    0.57
    findpost
    0.54
    splitlines
    0.54
     précisé
    0.49
    Jegyzetek
    0.49
    vini
    0.48
     Fabric
    0.48
    Sine
    0.47
     fabric
    0.47
    fabric
    0.47
    Activations Density 1.606%

    No Known Activations