© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12878
    Prev
    Next
    INDEX
    Explanations

    code blocks with parentheses and curly braces

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     disambiguazione
    -1.09
    MENAFN
    -1.04
    tvguidetime
    -0.97
     שוליים
    -0.95
    ImageContext
    -0.91
    homonymie
    -0.87
    脚注の使い方
    -0.86
     initComponents
    -0.84
    RegressionTest
    -0.83
    ModelSerializer
    -0.81
    POSITIVE LOGITS
    .
    0.57
    )
    0.47
    ),
    0.42
    <
    0.42
    (
    0.41
     educativas
    0.41
    \
    0.37
    $
    0.36
     creativos
    0.35
    :),
    0.35
    Activations Density 0.195%

    No Known Activations