© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12737
    Prev
    Next
    INDEX
    Explanations

    commas and periods within quotes.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     صوتيه
    -0.70
    iterranean
    -0.66
     itſelf
    -0.63
    ">',
    -0.58
    }$,
    -0.58
     تضيفلها
    -0.57
    🏻‍♀️
    -0.57
    Παραπομπές
    -0.57
    )$,
    -0.56
     \%$,
    -0.56
    POSITIVE LOGITS
     said
    1.07
    said
    0.83
     says
    0.79
     ”
    0.77
    ''
    0.73
    </blockquote>
    0.72
    ”
    0.68
     saith
    0.68
    ’’
    0.68
    </h3>
    0.67
    Activations Density 1.976%

    No Known Activations