© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10771
    Prev
    Next
    INDEX
    Explanations

    the verb "went" and other verbs describing movement or a change of state.

    oai_token-act-pair · gemini-2.0-flash

    went/gone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     now
    -0.65
    now
    -0.63
     was
    -0.62
     i
    -0.55
     Now
    -0.53
     got
    -0.50
    Now
    -0.50
     X
    -0.47
    idar
    -0.47
     not
    -0.46
    POSITIVE LOGITS
    RectangleBorder
    1.00
     Monfieur
    0.86
     Shakspeare
    0.86
     purpoſe
    0.84
     ſeveral
    0.84
    ſelves
    0.82
     ſtate
    0.81
    VIAF
    0.81
     houſe
    0.81
     Majefty
    0.81
    Activations Density 0.262%

    No Known Activations