© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3735
    Prev
    Next
    INDEX
    Explanations

    common function words and verbs in context

    oai_token-act-pair · gemini-2.0-flash

    let

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     تضيفلها
    -0.91
     myſelf
    -0.74
    +#+#
    -0.74
    ]")]
    -0.73
    aarrggbb
    -0.73
     المعيارى
    -0.73
    Hochspringen
    -0.72
    تقاوى
    -0.72
    DispatchToProps
    -0.71
     snippetHide
    -0.71
    POSITIVE LOGITS
     let
    2.55
     Let
    2.28
    let
    2.25
    Let
    2.17
     lets
    2.05
     letting
    2.03
     LET
    2.02
     Lets
    1.88
    lets
    1.88
    LET
    1.79
    Activations Density 1.217%

    No Known Activations