© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12706
    Prev
    Next
    INDEX
    Explanations

    mentions of sources of information

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     quienes
    -0.56
    toHaveBeenCalled
    -0.54
    intios
    -0.53
     who
    -0.53
     QtWidgets
    -0.50
     passaggio
    -0.49
     bacio
    -0.49
     invokingState
    -0.49
    Przypisy
    -0.48
    FXMLLoader
    -0.48
    POSITIVE LOGITS
     marketer
    0.86
     biographer
    0.86
     composer
    0.85
     investigator
    0.84
     guy
    0.84
     boss
    0.83
     manager
    0.81
     person
    0.81
     commander
    0.81
     editor
    0.80
    Activations Density 8.403%

    No Known Activations