© 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. 5094
    Prev
    Next
    INDEX
    Explanations

    entities (people, places, and things) mentioned in news or media, potentially with a focus on finance and measurement.

    oai_token-act-pair · gemini-2.0-flash

    Fabric/political discussions

    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
    Geplaatst
    -0.81
    AddTagHelper
    -0.69
    LookAnd
    -0.68
    passphrase
    -0.67
     Мексичка
    -0.65
    ChildScrollView
    -0.63
    цездатний
    -0.63
     незавершена
    -0.61
    fjspx
    -0.61
    Šaltiniai
    -0.60
    POSITIVE LOGITS
     Audiodateien
    0.70
    __*/
    0.58
    Clik
    0.53
     neutre
    0.53
    StringWriter
    0.49
     Helios
    0.44
     OPTIONAL
    0.44
     Coliseum
    0.43
     trinh
    0.41
    OrNil
    0.41
    Activations Density 14.365%

    No Known Activations