© 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. 13910
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and titles for people as well as conjunctions and punctuation

    oai_token-act-pair · gemini-2.0-flash

    technical terms and identifiers

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

    people's biographies

    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
     beseech
    -0.52
    Interment
    -0.51
    ::::::::::::::::
    -0.51
    enderror
    -0.49
    COME
    -0.49
     resembled
    -0.48
     COMING
    -0.47
     Sometime
    -0.47
    Enllaços
    -0.47
    parseFrom
    -0.46
    POSITIVE LOGITS
    tvguidetime
    0.58
     <>",
    0.57
     arşivlendi
    0.56
     AssemblyCulture
    0.54
     ontvangen
    0.54
     nakalista
    0.54
     holds
    0.53
    __':
    0.53
     counts
    0.52
     earned
    0.52
    Activations Density 1.346%

    No Known Activations