© 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. 4629
    Prev
    Next
    INDEX
    Explanations

    words related to dialogue, especially reported speech and agreements

    oai_token-act-pair · gemini-2.0-flash

    quotation marks and related punctuation

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

    Quote marks

    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
    “
    -1.36
     "
    -1.31
    {"
    -1.18
    ，“
    -1.18
     “
    -1.17
    "
    -1.16
    /"
    -1.14
    ["
    -1.14
    。“
    -1.12
    —“
    -1.07
    POSITIVE LOGITS
     ‘
    2.14
     '
    1.94
    『
    1.63
     (‘
    1.60
    、『
    1.39
    ‘
    1.31
     ('
    1.30
     ‚
    1.25
    。『
    1.25
    (‘
    1.21
    Activations Density 4.927%

    No Known Activations