© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12237
    Prev
    Next
    INDEX
    Explanations

    references to people's personal experiences and expressions.

    oai_token-act-pair · gemini-2.0-flash

    Dialogue and thoughts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    endpush
    -0.66
     виправивши
    -0.59
    PasswordEncoder
    -0.57
     Vikipedi
    -0.53
    ьаж
    -0.53
     OnTrigger
    -0.52
    )%
    -0.52
    AddTagHelper
    -0.51
    Билгалдахарш
    -0.51
     onOptions
    -0.50
    POSITIVE LOGITS
     given
    0.57
    ftagPool
    0.56
    spraak
    0.52
    findpost
    0.50
    Przypisy
    0.50
    endwhile
    0.48
     undercut
    0.47
    tivitas
    0.47
    given
    0.46
    eração
    0.46
    Activations Density 2.051%

    No Known Activations