© 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. 14610
    Prev
    Next
    INDEX
    Explanations

    words associated with stage productions and city streets

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating arrival or existence

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

    bringing something to life

    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
     houſe
    -0.87
     pleaſure
    -0.82
     greateſt
    -0.78
     ſever
    -0.77
     ſtate
    -0.76
     myſelf
    -0.76
     purpoſe
    -0.75
     becauſe
    -0.75
     fufficient
    -0.73
     beſt
    -0.73
    POSITIVE LOGITS
     come
    1.59
     brought
    1.27
    come
    1.27
     Come
    1.26
     COME
    1.25
     bring
    1.23
    Come
    1.19
     comes
    1.18
     Bring
    1.18
    Bring
    1.14
    Activations Density 0.934%

    No Known Activations