© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7339
    Prev
    Next
    INDEX
    Explanations

    mentions of land features specifically the phrase "surface runoff" and related terms like "soil".

    oai_token-act-pair · gemini-2.0-flash

    terms related to surface runoff

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

    surface

    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
    cerely
    -0.62
    نامج
    -0.61
    Datuak
    -0.61
     Baillargeon
    -0.56
    UnitTesting
    -0.54
    ClientSize
    -0.54
    MemoryWarning
    -0.53
    belly
    -0.52
    setContentView
    -0.51
    fuer
    -0.51
    POSITIVE LOGITS
    ">//
    0.55
     möjligt
    0.47
    kloped
    0.44
    vänt
    0.43
    NameInMap
    0.43
     healing
    0.42
    AsUp
    0.42
    НИК
    0.42
    OGND
    0.41
    гряз
    0.41
    Activations Density 2.938%

    No Known Activations