© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4263
    Prev
    Next
    INDEX
    Explanations

    sentences where the author is talking about themselves in relation to another person

    oai_token-act-pair · gemini-2.0-flash

    verbs related to actions or processes

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

    Subject doing something

    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
     venait
    -0.67
     sentito
    -0.63
     was
    -0.56
     blanches
    -0.55
     messo
    -0.55
    was
    -0.53
     bleef
    -0.53
     llevando
    -0.52
    zocht
    -0.52
     lät
    -0.52
    POSITIVE LOGITS
     hire
    0.81
     launch
    0.72
     offer
    0.71
     capture
    0.71
     save
    0.70
     wrap
    0.69
     try
    0.69
     turn
    0.69
     seal
    0.69
     brush
    0.68
    Activations Density 2.305%

    No Known Activations