© 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. 15202
    Prev
    Next
    INDEX
    Explanations

    words used in marketing and describing user experience/interactions

    oai_token-act-pair · gemini-2.0-flash

    computer-related technical text

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.66
    Personendaten
    -0.64
     "];
    -0.61
    chmal
    -0.60
    Diweddarwch
    -0.55
    iserie
    -0.55
    AppMethodBeat
    -0.55
     laikā
    -0.54
     numerus
    -0.54
     Pria
    -0.54
    POSITIVE LOGITS
    ArgsConstructor
    0.69
    AddTagHelper
    0.53
    новништво
    0.53
    findpost
    0.50
    TagHelper
    0.47
    Portale
    0.45
    ennifer
    0.45
     final
    0.44
     الحره
    0.42
    umman
    0.42
    Activations Density 0.514%

    No Known Activations