© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4776
    Prev
    Next
    INDEX
    Explanations

    words associated with understanding or thinking

    oai_token-act-pair · gemini-2.0-flash

    necessity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Porque
    -0.49
    mphs
    -0.48
     surla
    -0.46
     समीक्षक
    -0.45
     Öffentlichkeit
    -0.44
     خارجية
    -0.44
    Пото
    -0.44
    intre
    -0.44
    RTLU
    -0.44
    Should
    -0.43
    POSITIVE LOGITS
     necessary
    2.28
     required
    2.23
     needed
    2.14
    necessary
    2.13
    required
    1.95
     Necessary
    1.92
    needed
    1.92
     Required
    1.88
    Necessary
    1.86
     Needed
    1.80
    Activations Density 3.719%

    No Known Activations