© 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. 12172
    Prev
    Next
    INDEX
    Explanations

    the word "High" in relation to schools and German dialects, and also finds the name "Hirschfeld".

    oai_token-act-pair · gemini-2.0-flash

    High

    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
     High
    -2.17
    High
    -1.94
     HIGH
    -1.52
    HIGH
    -1.38
    high
    -1.23
     high
    -1.13
     Высо
    -0.96
    高
    -0.95
     高
    -0.94
     Low
    -0.91
    POSITIVE LOGITS
    principalTable
    0.68
    xymatrix
    0.60
     noDo
    0.59
    posób
    0.59
    AnimationsModule
    0.58
     africains
    0.56
    writerow
    0.55
     >>=
    0.53
     estekak
    0.53
    KommentareTeilen
    0.53
    Activations Density 1.310%

    No Known Activations