© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10497
    Prev
    Next
    INDEX
    Explanations

    a variety of positive buzzwords but especially the word drug

    oai_token-act-pair · gemini-2.0-flash

    free

    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
    SequentialGroup
    -0.75
    IUrlHelper
    -0.61
    djangoproject
    -0.61
    ніципалі
    -0.61
     hObject
    -0.59
     kaynağından
    -0.59
     useAppContext
    -0.58
     كومونز
    -0.57
    PageRoute
    -0.56
     Вікіпе
    -0.56
    POSITIVE LOGITS
     free
    1.04
    free
    0.81
    fre
    0.70
     fre
    0.68
     frees
    0.68
     freedom
    0.66
    自由
    0.65
     FRE
    0.64
     totally
    0.63
    REE
    0.63
    Activations Density 1.105%

    No Known Activations