© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7207
    Prev
    Next
    INDEX
    Explanations

    text related to advertising or marketing a business, particularly digital forms

    oai_token-act-pair · gemini-2.0-flash

    digital advertisement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    bootstrapcdn
    -0.88
     Referential
    -0.74
    URLException
    -0.67
    CompleteListener
    -0.64
    SuccessListener
    -0.64
     itſelf
    -0.63
     كومونز
    -0.63
     administrativos
    -0.63
     transfieras
    -0.63
     gynhyrchwyd
    -0.63
    POSITIVE LOGITS
    AndEndTag
    0.50
    aire
    0.38
     initComponents
    0.38
     دیده
    0.38
    ggar
    0.38
    рын
    0.38
     organically
    0.38
     scale
    0.38
     kork
    0.37
    räger
    0.37
    Activations Density 2.350%

    No Known Activations