© 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. 13365
    Prev
    Next
    INDEX
    Explanations

    phrases indicating justification or giving a reason, particularly those including the word "enough"

    oai_token-act-pair · gemini-2.0-flash

    the concept of "enough."

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

    enough

    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
    Rè
    -0.43
     []*
    -0.42
    orm
    -0.41
    :[]
    -0.40
     ThemeData
    -0.39
    [:]
    -0.39
    angsaan
    -0.39
     Paglinawan
    -0.39
    imia
    -0.38
    nata
    -0.37
    POSITIVE LOGITS
     enough
    3.45
    enough
    3.09
     Enough
    3.03
     ENOUGH
    2.80
    Enough
    2.73
     sufficient
    2.58
     genug
    2.47
     suficiente
    2.42
     genoeg
    2.31
     Sufficient
    2.31
    Activations Density 2.047%

    No Known Activations