© 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. 2203
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and equipment, possibly related to historical military or agricultural contexts

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb "pull"

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

    Towing vehicles

    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
    makeText
    -0.47
     Audiodateien
    -0.44
    runtime
    -0.44
    alisa
    -0.44
     _$
    -0.43
    affaires
    -0.41
    EndInit
    -0.40
     scrittore
    -0.39
     crucero
    -0.39
    setVerticalGroup
    -0.39
    POSITIVE LOGITS
     pulled
    1.17
     pulling
    1.17
     pull
    1.15
     pulls
    1.09
     Pulling
    1.08
     PULL
    1.05
    pulled
    1.05
     Pulled
    1.04
    pull
    1.02
     Pull
    1.01
    Activations Density 1.137%

    No Known Activations