© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12620
    Prev
    Next
    INDEX
    Explanations

    HTML table row syntax

    oai_token-act-pair · gemini-2.0-flash

    </tr>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    </tr>
    -2.00
     Мексичка
    -0.70
    TargetException
    -0.67
     \\
    -0.59
     houſe
    -0.59
     оригіналу
    -0.59
    lessness
    -0.56
     Efq
    -0.56
    lessly
    -0.55
    ScopeManager
    -0.55
    POSITIVE LOGITS
     FetchType
    0.72
    Demografie
    0.59
     GenerationType
    0.57
    Personendaten
    0.56
    <bos>
    0.54
    WithMany
    0.51
    决赛
    0.51
    adaptiveStyles
    0.50
     ProtoMessage
    0.50
    UserScript
    0.49
    Activations Density 1.087%

    No Known Activations