© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4670
    Prev
    Next
    INDEX
    Explanations

    words ending in "ble" or "tering" that describe problems

    oai_token-act-pair · gemini-2.0-flash

    unions and treaties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    JspWriter
    -0.68
     Loser
    -0.54
    Penjelasan
    -0.52
    low
    -0.51
    {%
    -0.50
    Loser
    -0.50
     Weak
    -0.50
     hini
    -0.49
    WEAK
    -0.49
    doPost
    -0.49
    POSITIVE LOGITS
     esternos
    0.71
    المناصب
    0.69
     unbroken
    0.63
    awtextra
    0.62
     unlimited
    0.60
     indisponible
    0.60
     impeccable
    0.60
     ModelExpression
    0.59
    NameInMap
    0.57
     AttributeSet
    0.56
    Activations Density 0.528%

    No Known Activations