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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3825
    Prev
    Next
    INDEX
    Explanations

    the names of people, especially Finnish people

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ValueStyle
    -0.82
    expandindo
    -0.77
    PerformLayout
    -0.61
    出版年
    -0.57
     calendriers
    -0.56
    ]")]
    -0.55
    })`
    -0.55
    ViewImports
    -0.54
     Infórmanos
    -0.54
    }\]
    -0.54
    POSITIVE LOGITS
     suivantes
    0.62
     blessés
    0.61
     suivants
    0.61
     juridiques
    0.60
     démocr
    0.60
     financières
    0.59
     complètes
    0.59
     quelcon
    0.58
     sélectionnez
    0.58
     médicaux
    0.58
    Activations Density 8.817%

    No Known Activations