© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5584
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs or indicators of tense in a sentence, as well as some references to proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    each

    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
    лыша
    -0.53
    temon
    -0.52
    entingan
    -0.42
    thanes
    -0.40
     AppModule
    -0.40
    Advert
    -0.39
    ɵɵ
    -0.38
     Menjadi
    -0.38
    깥
    -0.37
     Are
    -0.37
    POSITIVE LOGITS
     each
    3.08
    each
    2.48
     EACH
    2.23
    Each
    2.22
     Each
    2.17
    EACH
    2.09
     chacune
    1.80
     chacun
    1.78
     mỗi
    1.76
     ciascuno
    1.74
    Activations Density 3.712%

    No Known Activations