© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13776
    Prev
    Next
    INDEX
    Explanations

    code snippets that include the variable "ret" related to potential retries and bailing out

    oai_token-act-pair · gemini-2.0-flash

    ret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ret
    -2.53
     ret
    -2.27
    Ret
    -2.25
     Ret
    -2.08
    RET
    -1.90
     RET
    -1.54
    rets
    -1.32
    rett
    -1.13
    RETT
    -1.10
    retin
    -1.01
    POSITIVE LOGITS
    Autoritní
    0.53
    ógio
    0.49
     nakalista
    0.49
    OCCURRED
    0.47
    ença
    0.45
     dryer
    0.44
    tadır
    0.44
    quiera
    0.44
    redients
    0.44
    dui
    0.44
    Activations Density 2.173%

    No Known Activations