© 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. 8353
    Prev
    Next
    INDEX
    Explanations

    words indicating doubt or uncertainty and also the word "her".

    oai_token-act-pair · gemini-2.0-flash

    modifiers indicating degree or quantity

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

    somewhat

    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
     särskilt
    -0.83
     necessarily
    -0.82
     particolarmente
    -0.77
    rovna
    -0.77
     particularly
    -0.75
     særlig
    -0.75
     sonder
    -0.75
     particuli
    -0.74
     necesariamente
    -0.73
     besonders
    -0.72
    POSITIVE LOGITS
     Fairly
    0.85
     fairly
    0.83
     some
    0.73
     reasonably
    0.73
    Some
    0.69
    some
    0.69
     некото
    0.67
     somewhat
    0.67
     quelques
    0.66
     einiger
    0.66
    Activations Density 1.644%

    No Known Activations