© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4668
    Prev
    Next
    INDEX
    Explanations

    error handling code in Go

    oai_token-act-pair · gemini-2.0-flash

    nil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    rungsseite
    -0.80
     bezeichneter
    -0.65
    <bos>
    -0.57
     aught
    -0.55
    Legături
    -0.55
     FormsModule
    -0.55
    UnusedPrivate
    -0.55
     saites
    -0.54
     مشين
    -0.53
    FormBuilder
    -0.52
    POSITIVE LOGITS
    opsida
    0.56
    انيف
    0.52
    ParallelGroup
    0.52
    Tembelea
    0.52
     humain
    0.51
    istoitu
    0.51
    RTSC
    0.51
    GOTREF
    0.50
    HasColumnType
    0.50
    ISPR
    0.48
    Activations Density 2.005%

    No Known Activations