© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11758
    Prev
    Next
    INDEX
    Explanations

    numbers within square brackets

    oai_token-act-pair · gemini-2.0-flash

    science paper references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    mybatisplus
    -0.84
     }}"></
    -0.83
    Personensuche
    -0.82
    })*/
    -0.81
     ]
    -0.80
     reaſon
    -0.80
     himſelf
    -0.79
    ()]
    -0.78
     contextLoads
    -0.77
    Хьажоргаш
    -0.76
    POSITIVE LOGITS
    ,
    0.50
    O
    0.50
    &
    0.49
    tt
    0.47
    **
    0.44
    A
    0.44
    ;
    0.44
    bb
    0.43
    S
    0.43
    \
    0.42
    Activations Density 5.822%

    No Known Activations