© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15334
    Prev
    Next
    INDEX
    Explanations

    words that indicate subjectivity or time or classification

    oai_token-act-pair · gemini-2.0-flash

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Geplaatst
    -0.63
     AttributeSet
    -0.58
    ciatore
    -0.56
    Hentet
    -0.50
    KURZBESCHREIBUNG
    -0.49
     mergeFrom
    -0.48
     برانيه
    -0.48
     SqlDbType
    -0.47
    diyah
    -0.47
    megen
    -0.46
    POSITIVE LOGITS
    SharedCtor
    0.71
    :✨
    0.59
    HandlerContext
    0.58
    dymyr
    0.57
     lenker
    0.57
    ⓧ
    0.56
     Gazetteer
    0.54
    PyExc
    0.51
     Pardo
    0.49
     diſt
    0.47
    Activations Density 0.878%

    No Known Activations