© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5630
    Prev
    Next
    INDEX
    Explanations

    the suffix "ers"

    oai_token-act-pair · gemini-2.0-flash

    ers

    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
     Monfieur
    -1.59
     Majefty
    -1.55
    ers
    -1.51
     purpoſe
    -1.44
     Diſ
    -1.43
     Efq
    -1.41
     pleaſure
    -1.40
     Houſe
    -1.36
     Anſ
    -1.35
     Reſ
    -1.35
    POSITIVE LOGITS
     '
    0.63
    ,
    0.63
     James
    0.62
      
    0.61
    <eos>
    0.60
    -
    0.60
    '
    0.60
    <em>
    0.60
     "
    0.60
     de
    0.59
    Activations Density 0.322%

    No Known Activations