© 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. 8108
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by proper nouns or capitalized words often related to geopolitical locations or famous people and sports teams

    oai_token-act-pair · gemini-2.0-flash

    conjunctions and code-related keywords

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

    periods

    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
    ficulty
    -0.87
    gnition
    -0.85
    cknowledge
    -0.79
    iffance
    -0.78
    drawal
    -0.78
    ficult
    -0.78
    bunya
    -0.75
    ghijklmnop
    -0.75
    curacy
    -0.74
    polation
    -0.74
    POSITIVE LOGITS
    and
    0.61
    StoryboardSegue
    0.53
    for
    0.51
    or
    0.50
    jsonPath
    0.48
    AsUp
    0.48
    int
    0.48
    with
    0.47
    ink
    0.44
    here
    0.44
    Activations Density 3.950%

    No Known Activations