© 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. 6539
    Prev
    Next
    INDEX
    Explanations

    technical words relating to mechanical movement or manipulation

    oai_token-act-pair · gemini-2.0-flash

    Horizontal and vertical

    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
     ſp
    -0.65
     houſe
    -0.59
    ſelf
    -0.59
     Houſe
    -0.57
     laſt
    -0.57
     juſt
    -0.57
     getAge
    -0.56
     becauſe
    -0.56
    umbrella
    -0.56
     myſelf
    -0.55
    POSITIVE LOGITS
     horizontal
    0.99
    horizontal
    0.88
     vertical
    0.84
    Horizontal
    0.83
     Horizontal
    0.80
    vertical
    0.79
    Vertical
    0.77
     horizontally
    0.71
     Vertical
    0.68
    HORIZONTAL
    0.68
    Activations Density 1.456%

    No Known Activations