© 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. 10648
    Prev
    Next
    INDEX
    Explanations

    a variety of non-alphanumeric characters and digits

    oai_token-act-pair · gemini-2.0-flash

    Technical specs and discussions

    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
     R
    -0.66
     ten
    -0.65
     type
    -0.63
     B
    -0.63
     
    -0.62
     C
    -0.59
     H
    -0.59
     L
    -0.59
     I
    -0.58
     no
    -0.58
    POSITIVE LOGITS
    RenderAtEndOf
    0.94
     ―――――
    0.85
     Theſe
    0.84
     '\\;'
    0.84
    theless
    0.83
    IntoConstraints
    0.82
     photolibrary
    0.81
    expandindo
    0.76
    rizona
    0.75
     للاسماء
    0.75
    Activations Density 0.739%

    No Known Activations