© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2422
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with opinions on events, sometimes involving a sense of nostalgia or past events, often with the explicit word "never" nearby.

    oai_token-act-pair · gemini-2.0-flash

    never ever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     never
    -1.01
    never
    -0.91
     Never
    -0.91
    Never
    -0.90
     nigdy
    -0.88
     always
    -0.84
    Always
    -0.78
     nikdy
    -0.78
     NEVER
    -0.78
     nunca
    -0.77
    POSITIVE LOGITS
    endphp
    0.96
     CURIAM
    0.84
     }}"></
    0.82
    ])):
    0.80
     Wiktionnaire
    0.77
    +:+
    0.76
     TextInputType
    0.76
     JpaRepository
    0.75
    ]]:
    0.74
     eventdata
    0.73
    Activations Density 8.373%

    No Known Activations