© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7373
    Prev
    Next
    INDEX
    Explanations

    the phrase "lock-in" or tokens that are often near to it

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    довлет
    -0.57
     trasferimento
    -0.56
    criture
    -0.50
    KHR
    -0.49
    protoc
    -0.49
     GenerationType
    -0.48
    ]='\
    -0.46
    utica
    -0.46
    qat
    -0.46
    RequestHandler
    -0.46
    POSITIVE LOGITS
    MockBean
    0.65
     kasarigan
    0.64
    httphttps
    0.62
     autorytatywna
    0.58
     nahilalakip
    0.58
     '\\;'
    0.56
    jsxFileName
    0.56
     ExecuteAsync
    0.55
     ProtoMessage
    0.53
    angsaan
    0.52
    Activations Density 0.857%

    No Known Activations