© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6626
    Prev
    Next
    INDEX
    Explanations

    German words and phrases

    oai_token-act-pair · gemini-2.0-flash

    German and linguistics

    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
    Portály
    -0.75
    Portale
    -0.73
    estacks
    -0.68
     الرياضيه
    -0.67
     domestiques
    -0.66
     الرخصة
    -0.63
    zewod
    -0.61
    Tämä
    -0.61
    skjaer
    -0.61
    écnicas
    -0.60
    POSITIVE LOGITS
    ]<<
    0.40
    CloseOperation
    0.36
     Dateien
    0.31
    ]='\
    0.31
     SwitchCompat
    0.31
     saddest
    0.31
    mpo
    0.30
     <<<
    0.30
     MIT
    0.29
    moz
    0.28
    Activations Density 0.133%

    No Known Activations