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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1937
    Prev
    Next
    INDEX
    Explanations

    bits of code commonly found at the start of PHP blocks

    oai_token-act-pair · gemini-2.0-flash

    php tag

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ⓧ
    -0.87
    LookAnd
    -0.64
    FieldDescriptor
    -0.61
    PYX
    -0.56
     rax
    -0.52
    ⓘ
    -0.52
     मत
    -0.52
    protobuf
    -0.51
    twimg
    -0.51
     Az
    -0.50
    POSITIVE LOGITS
    ArgsConstructor
    0.65
     echo
    0.61
    ++$
    0.53
    सन्दर्भ
    0.52
    urbo
    0.50
    Hozzáférés
    0.50
     <>",
    0.49
     ECHO
    0.48
    echo
    0.48
     echoes
    0.48
    Activations Density 0.322%

    No Known Activations