© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11811
    Prev
    Next
    INDEX
    Explanations

    a multiword expression with "gotten out of control" or it finds discourse markers and pronouns

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    StoryboardSegue
    -0.84
     protoimpl
    -0.77
     صوتيه
    -0.73
     MainAxisSize
    -0.73
     للمعارف
    -0.73
    IndentedString
    -0.70
    posedge
    -0.69
    TagMode
    -0.65
    lapsingToolbar
    -0.64
     متعلقه
    -0.64
    POSITIVE LOGITS
     out
    2.66
     Out
    1.87
    out
    1.87
    Out
    1.81
     OUT
    1.71
    OUT
    1.44
     outta
    1.39
    出
    1.25
     fuori
    1.20
     outs
    1.16
    Activations Density 2.738%

    No Known Activations