© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3414
    Prev
    Next
    INDEX
    Explanations

    code snippets about alarms

    oai_token-act-pair · gemini-2.0-flash

    LENGTH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     between
    -0.49
    هاز
    -0.47
    hom
    -0.44
    èvent
    -0.43
    hdysval
    -0.43
    IAN
    -0.43
    between
    -0.43
    lements
    -0.42
     certain
    -0.42
    まれ
    -0.42
    POSITIVE LOGITS
     незавершена
    0.98
     Roskov
    0.91
    NameInMap
    0.91
    +#+#
    0.85
    Geplaatst
    0.82
    #+#
    0.81
    تقاوى
    0.81
    ItemBackground
    0.77
    IUrlHelper
    0.71
    :+:
    0.70
    Activations Density 1.075%

    No Known Activations