© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9441
    Prev
    Next
    INDEX
    Explanations

    words related to location and time, particularly in the context of geographic regions and dates

    oai_token-act-pair · gemini-2.0-flash

    North

    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
    TypedDataSet
    -0.69
    rungsseite
    -0.69
     оригіналу
    -0.67
    DeleteBehavior
    -0.59
     дописавши
    -0.52
    ագրություններ
    -0.49
     محفوظة
    -0.46
     CURIAM
    -0.46
    akhstan
    -0.44
    WhereInput
    -0.44
    POSITIVE LOGITS
     North
    2.92
    North
    2.72
     NORTH
    2.28
    NORTH
    1.92
    north
    1.70
     north
    1.52
    北
    1.47
     Север
    1.39
     北
    1.25
     norte
    1.20
    Activations Density 5.624%

    No Known Activations