© 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. 10007
    Prev
    Next
    INDEX
    Explanations

    references to locations

    oai_token-act-pair · gemini-2.0-flash

    positions/location

    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
     de
    -0.49
    ’
    -0.46
     Charter
    -0.45
     pok
    -0.45
    帖
    -0.45
     vừa
    -0.44
    alt
    -0.43
     may
    -0.43
    dataTables
    -0.43
     v
    -0.42
    POSITIVE LOGITS
    enumi
    0.76
     Efq
    0.75
    цездатний
    0.73
    RenderAtEndOf
    0.71
    extAlignment
    0.68
    yntaxException
    0.65
     تضيفلها
    0.65
     CreateTagHelper
    0.64
    CodedInputStream
    0.63
     itſelf
    0.63
    Activations Density 0.509%

    No Known Activations