© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 467
    Prev
    Next
    INDEX
    Explanations

    place names and Icelandic/Germanic names and words

    oai_token-act-pair · gemini-2.0-flash

    Icelandic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    djangoproject
    -0.75
    IContainer
    -0.60
    ReusableCell
    -0.56
    JNIEnv
    -0.51
    gonic
    -0.48
    jface
    -0.47
     varargin
    -0.47
    illots
    -0.46
    ṳ
    -0.45
    Statics
    -0.44
    POSITIVE LOGITS
     Icelandic
    0.91
     Reykjavik
    0.79
     Reykjav
    0.72
    RegistryLite
    0.70
     Iceland
    0.68
     Loki
    0.67
    ykjav
    0.67
     Wikimedijinoj
    0.66
    skjaer
    0.65
    setof
    0.65
    Activations Density 0.358%

    No Known Activations