© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14826
    Prev
    Next
    INDEX
    Explanations

    German sentences that express opinions or perceptions, especially those involving the verb "sein" (to be) and modal verbs.

    oai_token-act-pair · gemini-2.0-flash

    relative pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     itſelf
    -1.66
     myſelf
    -1.58
     ―――――
    -1.53
     Efq
    -1.51
     Monfieur
    -1.48
     purpoſe
    -1.47
     autorytatywna
    -1.47
     raiſ
    -1.46
    ſelf
    -1.45
     Theſe
    -1.45
    POSITIVE LOGITS
    ,
    1.02
     que
    0.91
    which
    0.90
     which
    0.89
     who
    0.86
    who
    0.86
    <eos>
    0.85
     что
    0.85
     whose
    0.83
     
    0.82
    Activations Density 0.370%

    No Known Activations