© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    mentions of aloe vera or other coupon codes.

    oai_token-act-pair · gemini-2.0-flash

    Skin care ingredients/coupons

    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
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.49
    Ārējās
    -0.47
    AddTo
    -0.46
     herbe
    -0.46
    anon
    -0.46
    lenburg
    -0.45
     upraw
    -0.45
     racc
    -0.44
     pes
    -0.43
    wpi
    -0.43
    POSITIVE LOGITS
    SharedCtor
    0.73
    IContainer
    0.67
     externi
    0.65
    MessageOf
    0.64
    SharedDtor
    0.60
    aarrggbb
    0.59
    contentLoaded
    0.56
    FormState
    0.54
    resave
    0.54
    hoeddwyd
    0.53
    Activations Density 0.405%

    No Known Activations