© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10293
    Prev
    Next
    INDEX
    Explanations

    sentences containing the words 'that', 'those', 'than', 'patients', or 'without'.

    oai_token-act-pair · gemini-2.0-flash

    Something is missing or without

    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
     no
    -0.95
     un
    -0.90
    no
    -0.87
    free
    -0.85
     нет
    -0.81
    No
    -0.79
     отсутствие
    -0.77
     free
    -0.76
    無
    -0.73
    无
    -0.71
    POSITIVE LOGITS
    RenderAtEndOf
    1.02
     المعيارى
    0.87
    +#+#
    0.82
     Chwiliwch
    0.77
     Numerade
    0.77
    ChildScrollView
    0.74
    脚注の使い方
    0.74
    oa̍t
    0.72
    ագրություններ
    0.72
    \}\\
    0.69
    Activations Density 0.790%

    No Known Activations