© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6682
    Prev
    Next
    INDEX
    Explanations

    elements of computer code

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.13
     '\\;'
    -0.71
    LookAnd
    -0.68
     Ammon
    -0.66
     Arka
    -0.65
     Arki
    -0.61
    ęcz
    -0.61
     offense
    -0.59
     Sito
    -0.58
     defenses
    -0.57
    POSITIVE LOGITS
    WaitGroup
    0.69
    INCREF
    0.63
     useStyles
    0.60
     Signalez
    0.58
    makeText
    0.56
     dauern
    0.56
    atimes
    0.56
    migrationBuilder
    0.55
     dauert
    0.54
     saites
    0.54
    Activations Density 0.781%

    No Known Activations