© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11207
    Prev
    Next
    INDEX
    Explanations

    the words "first", "second", "region", usually with "second" being most important

    oai_token-act-pair · gemini-2.0-flash

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     second
    -2.44
    Second
    -2.38
    second
    -2.30
     Second
    -2.16
    SECOND
    -2.00
     SECOND
    -1.89
     seconde
    -1.63
     segundo
    -1.59
    Secondly
    -1.58
     deuxième
    -1.52
    POSITIVE LOGITS
    bezier
    0.49
     EconPapers
    0.48
    MLLoader
    0.48
    gonic
    0.47
    oa̍t
    0.46
     виправивши
    0.44
     дописавши
    0.43
    AutoField
    0.42
     oprot
    0.42
    mudi
    0.41
    Activations Density 1.170%

    No Known Activations