© 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. 10119
    Prev
    Next
    INDEX
    Explanations

    passives expressed as "has/have/had been" followed by a past participle, but also triggers on shown, implemented, conventional and adhering.

    oai_token-act-pair · gemini-2.0-flash

    been

    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
     been
    -1.02
    been
    -0.92
    Been
    -0.90
     Been
    -0.82
     BEEN
    -0.81
     blown
    -0.56
     يتيمه
    -0.54
    біль
    -0.54
     été
    -0.52
    done
    -0.50
    POSITIVE LOGITS
    }\]
    0.58
    ']],
    0.57
    Württemberg
    0.56
      (
    0.56
    ;';
    0.56
    ']);
    0.55
    IndentedString
    0.54
     pronom
    0.54
    WireFormatLite
    0.53
    HSSF
    0.53
    Activations Density 0.184%

    No Known Activations