© 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. 1972
    Prev
    Next
    INDEX
    Explanations

    descriptive prose about people in nature in a historical story

    oai_token-act-pair · gemini-2.0-flash

    Describing a scene

    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
     whoſe
    -0.81
     Efq
    -0.80
     itſelf
    -0.79
    IVEREF
    -0.77
    GOTREF
    -0.76
     réfrig
    -0.73
     myſelf
    -0.73
     dévelo
    -0.72
     $_"
    -0.71
     himſelf
    -0.70
    POSITIVE LOGITS
     coming
    0.47
     sources
    0.46
     star
    0.46
    ومه
    0.45
     brand
    0.45
    uxxxx
    0.44
     f
    0.43
    ☉
    0.43
    +:+
    0.42
     pri
    0.42
    Activations Density 1.824%

    No Known Activations