© 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. 2200
    Prev
    Next
    INDEX
    Explanations

    mentions of issues, actions, or advice being contemplated over a variety of subjects.

    oai_token-act-pair · gemini-2.0-flash

    things

    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
     something
    -0.66
     things
    -0.64
     anything
    -0.63
     Something
    -0.62
    Something
    -0.61
     everything
    -0.60
    thing
    -0.60
    something
    -0.59
     Dinge
    -0.59
    anything
    -0.59
    POSITIVE LOGITS
     beginnetje
    0.54
    StoryboardSegue
    0.52
    msgSender
    0.52
    Personendaten
    0.49
    matchCondition
    0.47
    <bos>
    0.47
    uinal
    0.43
    bodyParser
    0.43
     nantinya
    0.43
    jspb
    0.42
    Activations Density 4.369%

    No Known Activations