© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15324
    Prev
    Next
    INDEX
    Explanations

    sentences that state a job title or the age of a person

    oai_token-act-pair · gemini-2.0-flash

    is/are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ymce
    -0.73
    <?
    -0.64
     الحره
    -0.61
    CodedInputStream
    -0.60
    XmlAccessorType
    -0.59
    PutMapping
    -0.57
    Legenda
    -0.57
    Viitteet
    -0.56
    GoogleApiClient
    -0.56
    ŚCI
    -0.55
    POSITIVE LOGITS
     CreateTagHelper
    0.64
     reported
    0.52
     oprot
    0.50
     behalf
    0.47
     reader
    0.46
     linkovi
    0.45
    LookAnd
    0.45
    OrNil
    0.45
    q
    0.45
     devoirs
    0.44
    Activations Density 1.642%

    No Known Activations