© 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. 12823
    Prev
    Next
    INDEX
    Explanations

    numbers and other symbols found in academic citations

    oai_token-act-pair · gemini-2.0-flash

    non-English language tokens

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

    1

    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
     estimés
    -0.63
    ècie
    -0.59
    énario
    -0.58
    ]")]
    -0.58
    esez
    -0.57
    openConnection
    -0.56
    Referanser
    -0.54
    bleshooting
    -0.54
    lihood
    -0.53
    )++;
    -0.53
    POSITIVE LOGITS
    zieć
    0.49
     diritti
    0.49
     –
    0.48
    SerializedName
    0.48
    اریخ
    0.48
    didSet
    0.46
    ядок
    0.46
    WithMany
    0.46
    moveToFirst
    0.45
     fome
    0.45
    Activations Density 1.293%

    No Known Activations