© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8297
    Prev
    Next
    INDEX
    Explanations

    terms related to cell biology and development in scientific literature

    oai_token-act-pair · gemini-2.0-flash

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ++)
    -0.68
    ?):
    -0.63
    ichtliche
    -0.62
    %)$
    -0.61
    ILLES
    -0.60
    [++
    -0.60
    ()}>
    -0.59
    }}">
    -0.59
    ()")
    -0.59
     kasarigan
    -0.59
    POSITIVE LOGITS
    <bos>
    1.13
     oreilles
    0.53
     fourrure
    0.52
    клопе
    0.50
     mobilité
    0.45
     cérami
    0.45
     religione
    0.42
    Alonso
    0.42
     felé
    0.42
     rembourse
    0.42
    Activations Density 5.410%

    No Known Activations