© 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. 5044
    Prev
    Next
    INDEX
    Explanations

    references to the recent past, especially "last night", "last week", and "yesterday."

    oai_token-act-pair · gemini-2.0-flash

    last

    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
    <?
    -0.79
    Vidite
    -0.74
     CreateTagHelper
    -0.56
    Collegamenti
    -0.53
     Roskov
    -0.50
    WithIOException
    -0.49
    OrBuilder
    -0.47
     past
    -0.46
    rrggbb
    -0.46
     últimas
    -0.45
    POSITIVE LOGITS
     resort
    0.71
    发表于
    0.69
    resort
    0.66
    исленность
    0.63
    StructEnd
    0.62
     minute
    0.60
    minute
    0.59
     fuo
    0.58
     Resort
    0.57
     resorts
    0.57
    Activations Density 0.797%

    No Known Activations