© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3867
    Prev
    Next
    INDEX
    Explanations

    various specifications and technical details regarding vehicular or mechanical components.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Geplaatst
    -0.77
    <bos>
    -0.71
     transférez
    -0.65
     utafitiHapana
    -0.63
    WriteTagHelper
    -0.62
    GEBURTSDATUM
    -0.60
    ])):
    -0.59
     Paglinawan
    -0.53
     ModelExpression
    -0.53
    Autoritní
    -0.52
    POSITIVE LOGITS
    InstanceState
    0.56
    ArgsConstructor
    0.55
     MainAxisSize
    0.54
    Viitteet
    0.52
    MENAFN
    0.52
    짝
    0.52
     pomy
    0.51
    ViewImports
    0.50
    eclampsia
    0.50
    otras
    0.49
    Activations Density 15.940%

    No Known Activations