© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12792
    Prev
    Next
    INDEX
    Explanations

    words related to heavy machinery using hydraulics

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to machinery and hydraulics

    np_token-act-pair-logits · gpt-4o-mini

    technical, machinery and agriculture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    +:+
    -0.63
     Mooney
    -0.52
     thema
    -0.52
    :"-"`
    -0.49
     переписи
    -0.48
     DEPART
    -0.47
     dreht
    -0.47
    CCI
    -0.47
     bord
    -0.47
     Zeug
    -0.47
    POSITIVE LOGITS
    RegressionTest
    0.86
    AndEndTag
    0.68
    يميديا
    0.58
    IBinder
    0.52
    MeasureSpec
    0.51
    CloseOperation
    0.50
    TestBed
    0.50
    Bibliographie
    0.50
     Abp
    0.50
    [++
    0.49
    Activations Density 0.845%

    No Known Activations