© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13907
    Prev
    Next
    INDEX
    Explanations

    words that suggest conflict, strong opinions, and disagreement

    oai_token-act-pair · gemini-2.0-flash

    Abstract concepts

    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
     Majefty
    -0.83
     itſelf
    -0.82
     myſelf
    -0.80
     Jefus
    -0.79
    rungsseite
    -0.76
     Theſe
    -0.75
     pleaſure
    -0.75
     Reſ
    -0.74
     houſe
    -0.73
     juſt
    -0.72
    POSITIVE LOGITS
     :
    0.49
    potranspiration
    0.44
    enoord
    0.42
     panas
    0.41
     ha
    0.41
    </table>
    0.41
    甸
    0.40
     cer
    0.40
    sätzlich
    0.40
    σμο
    0.40
    Activations Density 4.634%

    No Known Activations