© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10758
    Prev
    Next
    INDEX
    Explanations

    locations and geography, especially in Ireland

    oai_token-act-pair · gemini-2.0-flash

    Ireland locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     grand
    -0.56
    cassert
    -0.53
     cra
    -0.51
    endaftaran
    -0.50
    Примечания
    -0.50
    indrical
    -0.48
     Grand
    -0.48
    grand
    -0.47
    Literatur
    -0.47
    Билгалдахарш
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.80
     disambiguazione
    0.62
    AddTagHelper
    0.59
     resourceCulture
    0.57
    jspx
    0.56
     Efq
    0.56
    modb
    0.56
     فريبيس
    0.55
    ghijklmnop
    0.52
     devaient
    0.52
    Activations Density 0.815%

    No Known Activations