© 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. 3069
    Prev
    Next
    INDEX
    Explanations

    a variety of somewhat common words, sometimes in a cluster

    oai_token-act-pair · gemini-2.0-flash

    punctuation and quotation marks

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

    single quote

    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
    “
    -0.54
    ""}
    -0.53
     ")"
    -0.53
    OrBuilder
    -0.52
     "/"
    -0.51
     ";"
    -0.50
    ֖
    -0.48
     ")";
    -0.48
     ".";
    -0.47
    </h5>
    -0.47
    POSITIVE LOGITS
     '
    1.95
     ‘
    1.84
    ‘
    1.33
    ='
    1.33
    ('
    1.30
    、『
    1.30
    『
    1.25
    ,'
    1.23
     (‘
    1.23
     ('
    1.23
    Activations Density 0.115%

    No Known Activations