© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6581
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "back," especially in the context of returning or going back

    oai_token-act-pair · gemini-2.0-flash

    return / back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    帖最后由
    -0.75
     ProtoMessage
    -0.72
    EDEFAULT
    -0.68
    AndEndTag
    -0.66
     contextLoads
    -0.66
    AddTagHelper
    -0.66
    makeConstraints
    -0.65
    extAlignment
    -0.65
    TagMode
    -0.65
    RenderAtEndOf
    -0.64
    POSITIVE LOGITS
     back
    2.31
     Back
    1.98
    back
    1.94
    Back
    1.88
    BACK
    1.80
     BACK
    1.77
     return
    1.50
     Return
    1.49
    backs
    1.48
     tilbake
    1.47
    Activations Density 1.772%

    No Known Activations