© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14878
    Prev
    Next
    INDEX
    Explanations

    seemingly context-dependent words used in varied and possibly domain-specific topics.

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     educativos
    -0.54
     Drittan
    -0.52
    XtraGrid
    -0.52
    ladores
    -0.52
    TestingModule
    -0.51
    IActionResult
    -0.51
    жели
    -0.50
     ciebie
    -0.49
    glą
    -0.48
     laborales
    -0.48
    POSITIVE LOGITS
     CanadaChoose
    0.79
     »)
    0.75
     whereof
    0.65
    новниш
    0.64
     تضيفلها
    0.62
     Himo
    0.60
    ifornie
    0.59
    €)
    0.59
    <_>
    0.58
     utafitiHapana
    0.57
    Activations Density 7.066%

    No Known Activations