© 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. 4817
    Prev
    Next
    INDEX
    Explanations

    the word "stood" and words related to non-physical or artificial things

    oai_token-act-pair · gemini-2.0-flash

    virtual

    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
     the
    -1.09
     I
    -0.99
     an
    -0.96
     in
    -0.88
     C
    -0.88
     a
    -0.87
     it
    -0.87
     for
    -0.86
     G
    -0.85
     that
    -0.85
    POSITIVE LOGITS
     ―――――
    1.77
     ་་
    1.65
     Efq
    1.61
     myſelf
    1.59
     itſelf
    1.58
     Shakspeare
    1.55
     Reſ
    1.55
     Theſe
    1.50
     ――――
    1.46
     Anſ
    1.46
    Activations Density 1.622%

    No Known Activations