© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11199
    Prev
    Next
    INDEX
    Explanations

    various elements of scientific documents including figures, equations, Spanish nightlife and formal references

    oai_token-act-pair · gemini-2.0-flash

    physics/scientific equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    migrationBuilder
    -0.83
    SaveChangesAsync
    -0.79
    ClientSize
    -0.76
    \{\\
    -0.75
    KommentareTeilen
    -0.73
     houſe
    -0.69
    ::~
    -0.68
     %>%
    -0.68
    WriteBarrier
    -0.68
    ])));
    -0.68
    POSITIVE LOGITS
    AndEndTag
    0.54
     sockaddr
    0.48
    nk
    0.44
    IFR
    0.42
    Meld
    0.42
    צע
    0.42
     dod
    0.42
    InitStructure
    0.41
    Wester
    0.40
    PreferredItem
    0.40
    Activations Density 6.464%

    No Known Activations