© 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. 8886
    Prev
    Next
    INDEX
    Explanations

    php code, specifically references to the $_POST array and related functions like isset, filter and array_splice

    oai_token-act-pair · gemini-2.0-flash

    PHP web requests

    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
    hyrchwyd
    -0.69
     saites
    -0.59
     متعلقه
    -0.59
     O
    -0.57
     ویکی‌آمباردا
    -0.57
    thenReturn
    -0.56
     سكانية
    -0.54
     Италијани
    -0.54
     To
    -0.52
     sympathize
    -0.52
    POSITIVE LOGITS
    CardHeader
    0.59
    FetchType
    0.53
     LoginForm
    0.52
    JoinTable
    0.52
     Cæsar
    0.50
     groupName
    0.47
     Boletín
    0.46
     userSchema
    0.46
     Pues
    0.46
     TextFormField
    0.46
    Activations Density 3.837%

    No Known Activations