© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4944
    Prev
    Next
    INDEX
    Explanations

    words and punctuation indicative of a positive customer review

    oai_token-act-pair · gemini-2.0-flash

    variants of "can't" or "cannot"

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

    can't

    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
     Winaray
    -0.66
    IsMutable
    -0.56
    apimachinery
    -0.51
    .*")]
    -0.51
     referenties
    -0.50
    agissait
    -0.49
    锆
    -0.46
    odymium
    -0.46
     salmón
    -0.46
     sandstone
    -0.45
    POSITIVE LOGITS
     couldnt
    0.83
     couldn
    0.78
     Couldn
    0.78
    couldn
    0.73
     Cannot
    0.72
    Cannot
    0.70
     cant
    0.66
     cannot
    0.64
    cannot
    0.63
    cant
    0.61
    Activations Density 1.733%

    No Known Activations