© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14875
    Prev
    Next
    INDEX
    Explanations

    the cardinal directions 'East' and 'West'

    oai_token-act-pair · gemini-2.0-flash

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     iſt
    -1.02
     Anſ
    -1.02
     itſelf
    -0.97
     myſelf
    -0.96
     becauſe
    -0.93
     pleaſure
    -0.93
     Theſe
    -0.91
     ―――――
    -0.91
     Majefty
    -0.91
     purpoſe
    -0.90
    POSITIVE LOGITS
     in
    0.62
     /
    0.59
     I
    0.59
    /
    0.58
     a
    0.57
     on
    0.56
     per
    0.56
    ,
    0.55
     L
    0.53
    <eos>
    0.52
    Activations Density 0.130%

    No Known Activations