© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8120
    Prev
    Next
    INDEX
    Explanations

    words that describe characteristics or attributes of people

    oai_token-act-pair · gemini-2.0-flash

    words expressing qualities or characteristics

    np_token-act-pair-logits · gpt-4o-mini

    positive attributes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     Jefus
    -0.85
    felves
    -0.81
     itſelf
    -0.79
     houſe
    -0.78
     Houſe
    -0.77
    Cyfeiriadau
    -0.77
     myſelf
    -0.75
     becauſe
    -0.74
     himſelf
    -0.74
    uxxxx
    -0.73
    POSITIVE LOGITS
     sense
    0.54
     obvious
    0.51
     отношению
    0.48
     obviously
    0.47
     determined
    0.45
     Obviously
    0.45
     vision
    0.44
     natürlich
    0.43
     determination
    0.43
     compassion
    0.43
    Activations Density 1.116%

    No Known Activations