© 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. 9002
    Prev
    Next
    INDEX
    Explanations

    mentions of salt

    oai_token-act-pair · gemini-2.0-flash

    terms related to salt and salinity

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

    salt

    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
     Man
    -0.54
     Nath
    -0.54
     four
    -0.53
    TagMode
    -0.51
    绎
    -0.50
     Con
    -0.47
     man
    -0.47
     true
    -0.45
     Cap
    -0.45
     ten
    -0.44
    POSITIVE LOGITS
     Waray
    0.69
    oredCriteria
    0.62
     mapStateToProps
    0.62
     vinagre
    0.61
     headboard
    0.58
    ftagPool
    0.57
    UserScript
    0.57
    AndEndTag
    0.56
     leſs
    0.56
     getItemId
    0.55
    Activations Density 0.522%

    No Known Activations