© 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. 8821
    Prev
    Next
    INDEX
    Explanations

    words relating to places, events, and governing bodies

    oai_token-act-pair · gemini-2.0-flash

    forms of the word 'host'

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

    hosting

    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
    iets
    -0.56
    LookAnd
    -0.56
    getDoctrine
    -0.51
    extAlignment
    -0.48
    ogada
    -0.47
    BUMP
    -0.47
    makeConstraints
    -0.46
    jow
    -0.46
    पया
    -0.45
     ارت
    -0.45
    POSITIVE LOGITS
     host
    1.48
     hosts
    1.38
     hosting
    1.38
     hosted
    1.33
    host
    1.29
     Host
    1.26
     Hosting
    1.23
    Host
    1.20
     HOST
    1.20
    hosted
    1.19
    Activations Density 1.061%

    No Known Activations