© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15414
    Prev
    Next
    INDEX
    Explanations

    the word "no", often in association with a comma.

    oai_token-act-pair · gemini-2.0-flash

    the word 'No'

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

    no

    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
    Negative Logits
     kasarigan
    -0.88
     avoient
    -0.74
     étoient
    -0.73
     étrangères
    -0.65
     becauſe
    -0.64
     étoit
    -0.63
    InitVars
    -0.62
    orianCalendar
    -0.61
    TestingModule
    -0.61
     poveznice
    -0.61
    POSITIVE LOGITS
     matter
    0.67
    ,
    0.66
     way
    0.66
     need
    0.65
     manner
    0.65
    期刊论文
    0.61
     actually
    0.59
    msubsup
    0.56
    ConstraintMaker
    0.56
     room
    0.54
    Activations Density 2.196%

    No Known Activations