© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11550
    Prev
    Next
    INDEX
    Explanations

    Russian text, especially common words and punctuation

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    +#+#
    -1.00
     EconPapers
    -0.94
     nakalista
    -0.91
    MigrationBuilder
    -0.79
    RUnlock
    -0.77
    fromCharCode
    -0.77
    GEBURTSDATUM
    -0.76
     EClass
    -0.72
     linkovi
    -0.72
    ंदीखरीदारी
    -0.72
    POSITIVE LOGITS
    neſs
    0.59
     @"";
    0.55
    ()]);
    0.55
    ſelf
    0.55
    ėjas
    0.52
    leſs
    0.52
    fible
    0.50
    ®:
    0.50
    łbym
    0.50
     будешь
    0.50
    Activations Density 1.287%

    No Known Activations