© 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. 9094
    Prev
    Next
    INDEX
    Explanations

    location names such as lakes, rivers, cities or states, and also finds prepositions

    oai_token-act-pair · gemini-2.0-flash

    mentions of lakes or mountains

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

    Lake

    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
     الحره
    -0.65
    Predecesor
    -0.54
     vide
    -0.50
    Descarga
    -0.47
    printStackTrace
    -0.46
    enschaft
    -0.45
    vem
    -0.44
     facie
    -0.44
     disant
    -0.44
     seam
    -0.43
    POSITIVE LOGITS
     Lake
    1.16
     Mount
    1.06
    Lake
    1.01
    Mount
    0.96
     Mt
    0.88
     MOUNT
    0.84
     LAKE
    0.83
    Mt
    0.77
     فريبيس
    0.77
    LAKE
    0.73
    Activations Density 4.235%

    No Known Activations