© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11688
    Prev
    Next
    INDEX
    Explanations

    code snippets, tags and other document metadata related to HTML, XML and other web documents

    oai_token-act-pair · gemini-2.0-flash

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     OnInit
    -0.48
     post
    -0.46
     pos
    -0.45
    inata
    -0.44
    MENAFN
    -0.44
     "
    -0.44
     «
    -0.43
    fortawesome
    -0.43
     ideal
    -0.43
     ele
    -0.43
    POSITIVE LOGITS
     myſelf
    0.75
     tartalomajánló
    0.68
     Efq
    0.66
     Theſe
    0.65
     ―――――
    0.65
     ſeveral
    0.65
     itſelf
    0.64
     Diſ
    0.64
     متعلقه
    0.62
     uſe
    0.61
    Activations Density 0.748%

    No Known Activations