© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10563
    Prev
    Next
    INDEX
    Explanations

    superlative words and words stating something is the exception

    oai_token-act-pair · gemini-2.0-flash

    exclusively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -1.14
    примеча
    -0.75
     poveznice
    -0.69
    marle
    -0.67
     Garnet
    -0.63
    knapp
    -0.61
     الحره
    -0.60
     Orgel
    -0.60
    HandlerContext
    -0.59
     algun
    -0.59
    POSITIVE LOGITS
    marily
    0.56
    Mostly
    0.55
    HEAST
    0.54
     best
    0.52
     ALL
    0.48
     dataSnapshot
    0.48
    postmedia
    0.47
     Mostly
    0.46
    ient
    0.46
    ほぼ
    0.46
    Activations Density 1.642%

    No Known Activations