© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6131
    Prev
    Next
    INDEX
    Explanations

    the phrase "one of", and sometimes "most common".

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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>
    -1.57
     nahilalakip
    -0.75
    WithIOException
    -0.70
     egyik
    -0.60
     Signalez
    -0.59
    ंदीखरीदारी
    -0.59
     BoxDecoration
    -0.57
    +#+#
    -0.55
    tagHelperRunner
    -0.54
     AssemblyTitle
    -0.51
    POSITIVE LOGITS
    estars
    0.65
    hdashline
    0.65
     Heilig
    0.60
     fallu
    0.58
     Vikipedi
    0.57
    DataPropertyName
    0.55
    espère
    0.53
    ื่น
    0.51
    ORIAL
    0.51
    iries
    0.50
    Activations Density 0.250%

    No Known Activations