© 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. 8465
    Prev
    Next
    INDEX
    Explanations

    the word "geonomics" or parts of the word

    oai_token-act-pair · gemini-2.0-flash

    words related to geonomics

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

    ge

    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
    PerformLayout
    -0.50
    sunshine
    -0.45
    scratch
    -0.45
     Splash
    -0.44
     scratch
    -0.44
    labs
    -0.44
    IsContent
    -0.43
    ak
    -0.43
     Fürst
    -0.42
    der
    -0.42
    POSITIVE LOGITS
     onPostExecute
    0.75
     CreateTagHelper
    0.72
    Diweddarwch
    0.71
     فريبيس
    0.69
    таратура
    0.68
     externi
    0.68
     Signalez
    0.67
    ंदीखरीदारी
    0.63
    THISDAY
    0.63
    Diwedd
    0.63
    Activations Density 0.271%

    No Known Activations