© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5830
    Prev
    Next
    INDEX
    Explanations

    mentions of mineral springs and related activities

    oai_token-act-pair · gemini-2.0-flash

    hot springs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     المعيارى
    -0.86
    SequentialGroup
    -0.81
    IGraphics
    -0.76
     препратки
    -0.70
    KURZBESCHREIBUNG
    -0.69
    OrNil
    -0.67
    NewUrlParser
    -0.66
    bewerken
    -0.66
     ddelweddau
    -0.63
     الحره
    -0.58
    POSITIVE LOGITS
     hot
    1.30
     Hot
    1.16
    Hot
    1.15
    hot
    1.04
     spring
    0.94
     springs
    0.92
     thermal
    0.88
     HOT
    0.87
    HOT
    0.86
    spring
    0.81
    Activations Density 1.399%

    No Known Activations