© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2795
    Prev
    Next
    INDEX
    Explanations

    language about micro-credit programs reaching the world's poorest people

    oai_token-act-pair · gemini-2.0-flash

    poverty and deprivation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     poor
    -1.91
    Poor
    -1.75
     Poor
    -1.75
    poor
    -1.65
     POOR
    -1.63
     poorest
    -1.25
     poorer
    -1.23
     pobres
    -1.07
     pobre
    -1.05
     pauvres
    -0.88
    POSITIVE LOGITS
    adaptiveStyles
    0.54
    akterysty
    0.52
    RESUME
    0.50
    ngiliz
    0.50
    igail
    0.48
     createSlice
    0.47
     Trad
    0.47
    withOpacity
    0.47
    setupUi
    0.45
    amaño
    0.45
    Activations Density 2.753%

    No Known Activations