© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14653
    Prev
    Next
    INDEX
    Explanations

    the word "loud"

    oai_token-act-pair · gemini-2.0-flash

    loud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -2.44
    '
    -0.86
     the
    -0.71
    ↵↵
    -0.60
    ’
    -0.57
    The
    -0.56
     were
    -0.50
     still
    -0.49
    A
    -0.49
    Is
    -0.47
    POSITIVE LOGITS
     HasFactory
    1.02
     OnInit
    1.01
    bootstrapcdn
    0.93
     TextInputType
    0.84
     AssemblyVersion
    0.83
    GenerationType
    0.82
    ardians
    0.81
    fromnode
    0.81
     AssemblyCulture
    0.80
    onnaissance
    0.79
    Activations Density 1.660%

    No Known Activations