© 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. 7205
    Prev
    Next
    INDEX
    Explanations

    sentence fragments followed by bullet points or parentheses and the words "so" and "but".

    oai_token-act-pair · gemini-2.0-flash

    speaking

    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
     typelib
    -0.62
     Blat
    -0.54
    Personensuche
    -0.54
     klart
    -0.52
    bestimmung
    -0.52
    Попис
    -0.52
     newList
    -0.52
    ecore
    -0.49
    TargetException
    -0.49
    MigrationBuilder
    -0.48
    POSITIVE LOGITS
     speaking
    2.94
     Speaking
    2.52
    speaking
    2.50
    Speaking
    2.41
     speak
    2.05
     spoke
    1.75
     Speak
    1.70
     speaks
    1.66
    speak
    1.66
     parlant
    1.64
    Activations Density 0.732%

    No Known Activations