© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3976
    Prev
    Next
    INDEX
    Explanations

    time progressing and getting harder

    oai_token-act-pair · gemini-2.0-flash

    changes and difficulties

    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
     gradually
    -0.65
    óa
    -0.58
     Gradually
    -0.57
     coraz
    -0.57
     ""],
    -0.56
    testens
    -0.56
     changed
    -0.54
    ANTLR
    -0.54
    ValueStyle
    -0.54
    SourceChecksum
    -0.52
    POSITIVE LOGITS
     مرئيه
    0.64
    resizingMask
    0.63
    reuung
    0.56
     výbě
    0.55
    まま
    0.53
     låg
    0.52
    irability
    0.50
     izvē
    0.50
    ntä
    0.49
    inette
    0.48
    Activations Density 10.577%

    No Known Activations