© 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. 11709
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names with various words surrounding them

    oai_token-act-pair · gemini-2.0-flash

    Someone is saying 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_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
     say
    -1.02
    say
    -0.82
     recommend
    -0.69
    RenderAtEndOf
    -0.66
     SAY
    -0.65
    \{\\
    -0.64
     think
    -0.63
     believe
    -0.62
    Say
    -0.61
     imagine
    -0.60
    POSITIVE LOGITS
     states
    1.10
     notes
    0.99
     reports
    0.87
    states
    0.87
     States
    0.83
    States
    0.83
     calls
    0.82
     STATES
    0.77
     plans
    0.73
    reports
    0.73
    Activations Density 4.872%

    No Known Activations