© 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. 15714
    Prev
    Next
    INDEX
    Explanations

    German language text fragments related to sentence construction, particulary around the usage of verbs with the words 'Brief' (letter) and 'Satz' (sentence).

    oai_token-act-pair · gemini-2.0-flash

    German text

    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
     the
    -0.74
     he
    -0.59
     The
    -0.54
     my
    -0.49
    The
    -0.48
     me
    -0.48
    ...
    -0.47
     
    -0.45
     (
    -0.45
    ,
    -0.44
    POSITIVE LOGITS
     itſelf
    1.03
    AndEndTag
    1.02
     Efq
    1.01
     ſever
    0.93
     myſelf
    0.90
     unſ
    0.88
     raiſ
    0.86
     Monfieur
    0.84
     ſeveral
    0.84
     Chriftian
    0.83
    Activations Density 0.376%

    No Known Activations