© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9708
    Prev
    Next
    INDEX
    Explanations

    text that starts with a newline, a space, then a number, and then another number

    oai_token-act-pair · gemini-2.0-flash

    Dates and political events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    #+#
    -0.69
     Италијани
    -0.62
    mybatisplus
    -0.60
    цездатний
    -0.59
    Autoritní
    -0.58
    ModelAdmin
    -0.57
    oredCriteria
    -0.56
     encomp
    -0.56
     Exactos
    -0.56
    évaluateur
    -0.55
    POSITIVE LOGITS
    Enllaces
    0.71
     propOrder
    0.59
     nakalista
    0.57
    IBAction
    0.53
    PRNewswire
    0.51
    openConnection
    0.50
    DrawerLayout
    0.49
    addContainerGap
    0.48
     MainAxisSize
    0.48
    GroupLayout
    0.47
    Activations Density 1.478%

    No Known Activations