© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14452
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or groups of locations

    oai_token-act-pair · gemini-2.0-flash

    countries

    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
    enumi
    -0.70
    ]")]
    -0.61
     lenker
    -0.59
     Sub
    -0.58
    IsMutable
    -0.56
    bbons
    -0.55
    Hozzáférés
    -0.55
    ubscribe
    -0.54
    RESUMO
    -0.54
     nakalista
    -0.53
    POSITIVE LOGITS
     ſche
    0.57
    IntoConstraints
    0.50
    GTCX
    0.50
     ſtate
    0.50
    Demografie
    0.49
    spec
    0.48
    fgets
    0.47
    tvguidetime
    0.47
    FundMe
    0.45
    そも
    0.45
    Activations Density 1.532%

    No Known Activations