© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4410
    Prev
    Next
    INDEX
    Explanations

    punctuation, question-answer exchanges, and certain pronouns in sequences of dialogue.

    oai_token-act-pair · gemini-2.0-flash

    punctuation and specific question formats

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

    question/response snippets

    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
     lenker
    -0.55
     متعلقه
    -0.54
    ografija
    -0.52
    lably
    -0.46
     مشين
    -0.45
     nett
    -0.44
    roek
    -0.44
    abetes
    -0.44
     inspiri
    -0.43
     Cual
    -0.43
    POSITIVE LOGITS
    ]")]
    0.75
     remember
    0.72
     how
    0.63
    ագրություններ
    0.62
     المعيارى
    0.58
    gangenheit
    0.57
    principalTable
    0.57
     Remember
    0.56
    remember
    0.54
    iredo
    0.54
    Activations Density 1.100%

    No Known Activations