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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11781
    Prev
    Next
    INDEX
    Explanations

    the string 'oc' followed by some other characters

    oai_token-act-pair · gemini-2.0-flash

    terms related to object-oriented programming or class structures

    np_token-act-pair-logits · gpt-4o-mini

    oc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ora
    -0.48
     more
    -0.42
    leggen
    -0.42
     uffic
    -0.41
    hat
    -0.40
    談社
    -0.40
     Staten
    -0.40
     B
    -0.39
    ol
    -0.39
    ou
    -0.39
    POSITIVE LOGITS
    ViewFeatures
    0.82
     userSchema
    0.73
    rrggbb
    0.69
     jdbcTemplate
    0.69
     wireType
    0.68
     تضيفلها
    0.68
     DriverManager
    0.65
     ostavi
    0.65
     CGRect
    0.64
     henvisninger
    0.63
    Activations Density 0.498%

    No Known Activations