© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11779
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially PHP, and words associated with website administration

    oai_token-act-pair · gemini-2.0-flash

    Admin/login

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    SourceChecksum
    -0.90
     AssemblyCulture
    -0.86
    MigrationBuilder
    -0.83
    帖最后由
    -0.81
    исленность
    -0.81
     виправивши
    -0.79
     pinulongan
    -0.77
    Билгалдахарш
    -0.76
    GEBURTSDATUM
    -0.76
    ]")]
    -0.73
    POSITIVE LOGITS
     juges
    0.43
    碁
    0.42
     fekete
    0.41
     pères
    0.41
    fml
    0.40
    relser
    0.39
     devlet
    0.39
     white
    0.39
     religieuses
    0.38
     yanında
    0.38
    Activations Density 0.319%

    No Known Activations