© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2347
    Prev
    Next
    INDEX
    Explanations

    references to things being neglected or overlooked

    oai_token-act-pair · gemini-2.0-flash

    overlooked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Widths
    -0.54
    躇
    -0.51
    oform
    -0.49
    leih
    -0.48
    StoredProcedure
    -0.48
    phthal
    -0.45
     endregion
    -0.45
     wiecz
    -0.45
     cref
    -0.45
    ắp
    -0.45
    POSITIVE LOGITS
     Walkover
    0.64
    GEBURTSDATUM
    0.62
     يتيمه
    0.61
    UnusedPrivate
    0.61
    featureID
    0.60
    ValueStyle
    0.60
    contentLoaded
    0.58
    VersionUID
    0.57
    Personendaten
    0.57
     beginnetje
    0.55
    Activations Density 1.179%

    No Known Activations