© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6608
    Prev
    Next
    INDEX
    Explanations

    actions and states of being described using different verb tenses

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    MigrationBuilder
    -0.95
    RenderAtEndOf
    -0.80
    +#+
    -0.79
     itſelf
    -0.77
     iſt
    -0.75
     myſelf
    -0.75
    ſelves
    -0.73
     ſta
    -0.72
     reaſon
    -0.72
     Anſ
    -0.71
    POSITIVE LOGITS
     pourtant
    0.47
     get
    0.45
    กัน
    0.44
     pre
    0.43
    хождение
    0.42
     
    0.42
     make
    0.42
    fordert
    0.40
     vie
    0.40
     O
    0.40
    Activations Density 7.040%

    No Known Activations