© 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. 2410
    Prev
    Next
    INDEX
    Explanations

    the letter "O" followed by another character or number

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'O'

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

    O

    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
    expandindo
    -1.07
    RenderAtEndOf
    -0.98
    AccessorTable
    -0.86
    ItemBackground
    -0.85
     समीक्षक
    -0.85
     resourceCulture
    -0.83
    MessageOf
    -0.83
    MigrationBuilder
    -0.82
    :✨
    -0.81
    UnusedPrivate
    -0.81
    POSITIVE LOGITS
    ap
    0.41
    a
    0.41
    in
    0.40
    al
    0.39
    an
    0.39
    ar
    0.38
    ue
    0.38
    ibm
    0.38
    ble
    0.37
    ah
    0.36
    Activations Density 0.966%

    No Known Activations