© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4439
    Prev
    Next
    INDEX
    Explanations

    HTML paragraph and heading tags

    oai_token-act-pair · gemini-2.0-flash

    HTML heading tag

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    httphttps
    -1.11
     الحره
    -1.09
     <<<<<<<<<<<<<<
    -1.02
     disambiguazione
    -1.02
     متعلقه
    -1.01
     للمعارف
    -0.88
     '\\;'
    -0.87
    ArgsConstructor
    -0.83
    SharedDtor
    -0.82
    存于互联网档案馆
    -0.82
    POSITIVE LOGITS
    воро
    0.42
    <eos>
    0.41
    вобо
    0.41
     saveur
    0.41
    RES
    0.40
    boxed
    0.39
    Демографія
    0.38
    過ごし
    0.37
     afforded
    0.37
     The
    0.37
    Activations Density 0.417%

    No Known Activations