© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9448
    Prev
    Next
    INDEX
    Explanations

    language related to costs and economic comparisons

    oai_token-act-pair · gemini-2.0-flash

    cost

    np_max-act · gemini-2.0-flash

    cost

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -1.16
     SIMBAD
    -0.88
     propOrder
    -0.85
     '\\;'
    -0.79
    Бахар
    -0.78
    ftagPool
    -0.77
     myſelf
    -0.77
     AssemblyVersion
    -0.77
    rungsseite
    -0.77
     дописавши
    -0.77
    POSITIVE LOGITS
     оригіналу
    0.49
    </tr>
    0.47
     Another
    0.46
    ера
    0.46
    ruf
    0.45
     Far
    0.44
    nextLine
    0.44
    くな
    0.44
     “
    0.43
    </h1>
    0.43
    Activations Density 7.204%

    No Known Activations