© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4621
    Prev
    Next
    INDEX
    Explanations

    Latex or other math markup

    oai_token-act-pair · gemini-2.0-flash

    }^{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     }^{
    -2.25
     }^{\
    -1.50
     }^{-
    -1.27
     }_{
    -1.08
     }^{*}$
    -1.04
     }^{*}
    -1.00
     }^{[
    -1.00
     }^{(
    -0.98
     }^{*
    -0.98
     }_{\
    -0.95
    POSITIVE LOGITS
    DoubleQuotes
    0.51
     deco
    0.49
    gratis
    0.47
    deco
    0.46
    клопе
    0.45
     걸
    0.45
    neighbor
    0.41
    ngdoc
    0.40
    Member
    0.40
    子
    0.40
    Activations Density 1.020%

    No Known Activations