© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12253
    Prev
    Next
    INDEX
    Explanations

    mentions of accounting or search engines in a technical context

    oai_token-act-pair · gemini-2.0-flash

    Accounting and search engines

    np_max-act · gemini-2.0-flash
    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
     Cæsar
    -0.82
     Majefty
    -0.79
     Reſ
    -0.78
     Monfieur
    -0.77
     Diſ
    -0.76
    OGND
    -0.75
     fevere
    -0.75
     ―――――
    -0.75
     Conſ
    -0.74
     Perſ
    -0.74
    POSITIVE LOGITS
    migrationBuilder
    0.74
    audiovisuel
    0.67
    dialement
    0.65
    __':
    0.60
    Vidéo
    0.60
    ressee
    0.59
     Strukturen
    0.58
    Amicalement
    0.57
     the
    0.57
    󠁿
    0.57
    Activations Density 0.558%

    No Known Activations