© 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. 4798
    Prev
    Next
    INDEX
    Explanations

    the word "fail", sometimes also activating a nearby word

    oai_token-act-pair · gemini-2.0-flash

    fail

    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
    @[+][
    -0.67
    ,
    -0.66
     as
    -0.59
     Edwards
    -0.59
    ck
    -0.57
     or
    -0.56
    мен
    -0.56
    ti
    -0.54
    ark
    -0.53
    mar
    -0.52
    POSITIVE LOGITS
     Theſe
    1.05
     Jefus
    1.01
     Reſ
    1.00
     itſelf
    0.98
    AddTagHelper
    0.98
     pleaſure
    0.98
     Monfieur
    0.96
    .")
    0.95
     photolibrary
    0.94
     ་་
    0.93
    Activations Density 2.153%

    No Known Activations