© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4427
    Prev
    Next
    INDEX
    Explanations

    words related to the effects of forests and vegetation on water flow, harvesting, and soil erosion

    oai_token-act-pair · gemini-2.0-flash

    Ecological and land management

    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
    amá
    -0.53
    UTERS
    -0.52
    nytimes
    -0.51
     defaultstate
    -0.50
    SIGNAL
    -0.50
    ViewChild
    -0.49
    MathML
    -0.48
     nakalista
    -0.48
    KommentareTeilen
    -0.48
    syn
    -0.48
    POSITIVE LOGITS
     ProtoMessage
    0.79
    oa̍t
    0.73
    RenderAtEndOf
    0.70
    moveToFirst
    0.64
    Portale
    0.57
     ſta
    0.57
    DeleteBehavior
    0.57
    IndentedString
    0.54
     protoimpl
    0.51
     ModelExpression
    0.50
    Activations Density 3.783%

    No Known Activations