© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12614
    Prev
    Next
    INDEX
    Explanations

    keywords in Java code like 'public,' 'class', and 'private'

    oai_token-act-pair · gemini-2.0-flash

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    تماد
    -0.45
     상세
    -0.44
    Soorten
    -0.44
    że
    -0.43
     ویکی‌آمباردا
    -0.43
     security
    -0.42
    GMENT
    -0.42
     Security
    -0.41
     B
    -0.41
    hoea
    -0.41
    POSITIVE LOGITS
     purpoſe
    0.88
    SBATCH
    0.85
     nahilalakip
    0.84
     chofe
    0.84
     reaſon
    0.83
     ſtate
    0.82
     anſ
    0.82
     Efq
    0.82
     ſche
    0.80
     fhew
    0.78
    Activations Density 0.815%

    No Known Activations