© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    sentences describing actions of people with titles at a company

    oai_token-act-pair · gemini-2.0-flash

    forms of the word 'step'

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

    step

    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
    etragen
    -0.52
    saraba
    -0.49
    ourtney
    -0.44
     économ
    -0.43
    født
    -0.43
    audrait
    -0.42
    INSEE
    -0.42
    ीक
    -0.41
    zyż
    -0.40
    argli
    -0.40
    POSITIVE LOGITS
     step
    1.82
    step
    1.70
     stepping
    1.70
    Step
    1.67
     Step
    1.66
     stepped
    1.66
     Stepping
    1.45
     steps
    1.43
     STEP
    1.43
    stepping
    1.42
    Activations Density 1.787%

    No Known Activations