© 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. 8090
    Prev
    Next
    INDEX
    Explanations

    features of persuasive writing, where points are made and then supporting evidence or instructions are given

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to software or programming

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

    punctuation

    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
     ddelweddau
    -0.54
    SourceChecksum
    -0.52
     weren
    -0.47
     wearer
    -0.46
    setGravity
    -0.44
    Couldn
    -0.44
    kind
    -0.44
     qualitative
    -0.44
    illoin
    -0.43
     didnt
    -0.43
    POSITIVE LOGITS
    gameserver
    0.63
    Referencer
    0.55
    AutoScale
    0.55
    resave
    0.54
     declare
    0.54
    kinci
    0.54
     sẻ
    0.53
     learn
    0.53
    printStackTrace
    0.52
    endphp
    0.52
    Activations Density 2.422%

    No Known Activations