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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13621
    Prev
    Next
    INDEX
    Explanations

    java or javascript code

    oai_token-act-pair · gemini-2.0-flash

    }

    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
     ویکی‌پدی
    -0.58
    Jeografia
    -0.56
    PreferredItem
    -0.53
    зулта
    -0.49
    lido
    -0.49
     Li
    -0.48
    —
    -0.45
    ard
    -0.45
    Li
    -0.44
    elten
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.73
     Monfieur
    0.73
     Efq
    0.71
     myſelf
    0.70
     himſelf
    0.69
     themſelves
    0.65
     getItemId
    0.64
     itſelf
    0.62
    CGRectMake
    0.61
     дописавши
    0.60
    Activations Density 3.413%

    No Known Activations