© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3456
    Prev
    Next
    INDEX
    Explanations

    varied words and phrases that provide general context to a story

    oai_token-act-pair · gemini-2.0-flash

    down

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    cyjnych
    -0.54
    তথ্যসূত্র
    -0.50
    ή
    -0.50
    cznych
    -0.47
    letzt
    -0.45
     psycopg
    -0.45
    })->
    -0.44
    出版年
    -0.44
    cyjny
    -0.44
    tvguidetime
    -0.44
    POSITIVE LOGITS
     down
    3.14
    down
    2.61
    Down
    2.52
     Down
    2.52
     DOWN
    2.34
    DOWN
    2.06
    downs
    1.77
    ダウン
    1.52
     dow
    1.47
     downs
    1.47
    Activations Density 2.852%

    No Known Activations