© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13681
    Prev
    Next
    INDEX
    Explanations

    words indicating that something is happening, real, or factual.

    oai_token-act-pair · gemini-2.0-flash

    adjectives indicating intensity or impact

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

    High intensity

    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
    Geplaatst
    -0.67
    UnusedPrivate
    -0.60
    MENAFN
    -0.58
    MetaObject
    -0.56
    Injured
    -0.54
    Хьажоргаш
    -0.52
    BeginContext
    -0.51
     Roskov
    -0.50
    WriteBarrier
    -0.49
     пунктов
    -0.49
    POSITIVE LOGITS
     significant
    1.08
     severe
    0.99
     considerable
    0.98
     immense
    0.98
    significant
    0.96
     greater
    0.95
    considerable
    0.92
    Significant
    0.91
     profound
    0.91
     enormous
    0.90
    Activations Density 4.876%

    No Known Activations