© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7748
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" followed by other words like "a", "the", "their", and numbers, often within phrases indicating time or purpose.

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     MainAxisSize
    -0.67
    HtmlAttribute
    -0.67
     ***!
    -0.65
    Personensuche
    -0.65
     GoogleFonts
    -0.65
    stdc
    -0.63
    mobileqq
    -0.63
    tagHelperRunner
    -0.63
    Архівовано
    -0.61
     extérieurs
    -0.59
    POSITIVE LOGITS
     pases
    0.53
     Réponses
    0.52
    zani
    0.46
     length
    0.45
    omo
    0.44
     عب
    0.44
     kind
    0.44
     Inc
    0.43
    如下
    0.43
     inc
    0.42
    Activations Density 1.666%

    No Known Activations