© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10839
    Prev
    Next
    INDEX
    Explanations

    words related to gaseous emissions and toxic chemicals

    oai_token-act-pair · gemini-2.0-flash

    environmental toxins and chemicals

    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
    featureID
    -0.80
    LookAnd
    -0.65
    UseVisualStyle
    -0.63
     surla
    -0.61
    ⓧ
    -0.59
    ViewFeatures
    -0.59
    tagHelper
    -0.56
     свер
    -0.56
     chi̍t
    -0.56
    hilt
    -0.55
    POSITIVE LOGITS
    клопе
    0.52
     DCM
    0.44
    MethodImpl
    0.44
     Weib
    0.44
    ambito
    0.43
    slidesPer
    0.42
     epist
    0.42
    URLException
    0.41
    migrationBuilder
    0.41
     reclaimed
    0.41
    Activations Density 1.936%

    No Known Activations