© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13522
    Prev
    Next
    INDEX
    Explanations

    words loosely related to events taking place during a narrative, including sports, personal events, and fantasy.

    oai_token-act-pair · gemini-2.0-flash

    sports and night

    np_max-act · gemini-2.0-flash

    say "punctuation"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    met
    -0.48
     me
    -0.44
    #
    -0.43
    &
    -0.43
    su
    -0.42
     imperio
    -0.41
    вили
    -0.41
     fæ
    -0.41
    ata
    -0.40
    capa
    -0.40
    POSITIVE LOGITS
     فريبيس
    1.02
    ſelf
    0.92
    BagLayout
    0.91
     itſelf
    0.85
    تقاوى
    0.85
    fjspx
    0.84
     ་་
    0.83
    RenderAtEndOf
    0.82
    béco
    0.81
     myſelf
    0.81
    Activations Density 1.007%

    No Known Activations