© 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. 8453
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people, companies, or political things

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs

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

    News and commentary

    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
     oprot
    -0.41
    rafas
    -0.41
    yarnpkg
    -0.41
     LinkedHashMap
    -0.40
    Ok
    -0.40
    numerusform
    -0.40
    GetMapping
    -0.39
    bParam
    -0.39
     나는
    -0.38
     airplane
    -0.38
    POSITIVE LOGITS
     was
    0.84
     is
    0.79
     forgot
    0.76
     didn
    0.75
     did
    0.74
     knows
    0.74
     isn
    0.72
     knew
    0.72
     wasn
    0.71
     threw
    0.69
    Activations Density 3.933%

    No Known Activations