© 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. 13170
    Prev
    Next
    INDEX
    Explanations

    numerical data, extracted information and certain phrases or words related to extraction and rights.

    oai_token-act-pair · gemini-2.0-flash

    Formal data and documents

    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
     CreateTagHelper
    -0.58
     논
    -0.56
    VersionUID
    -0.52
    Ссылки
    -0.51
    ArgsConstructor
    -0.50
    Ethylbenzene
    -0.49
     становника
    -0.48
    ReusableCell
    -0.48
    Hentet
    -0.48
    stry
    -0.47
    POSITIVE LOGITS
     âgées
    0.64
     Италијани
    0.64
    tagext
    0.58
     NEST
    0.58
    EndGlobalSection
    0.56
    webElementGuid
    0.55
     AppCompatTheme
    0.53
     CWE
    0.53
    titleMargin
    0.53
     Numerade
    0.52
    Activations Density 2.626%

    No Known Activations