© 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. 11860
    Prev
    Next
    INDEX
    Explanations

    verbs that describe actions being taken

    oai_token-act-pair · gemini-2.0-flash

    in

    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
     المعيارى
    -0.80
    ちな
    -0.59
    Datuak
    -0.58
    protoimpl
    -0.53
    ksikon
    -0.48
    leville
    -0.48
     utafitiHapana
    -0.47
     Oester
    -0.47
    bewerken
    -0.47
    andReturn
    -0.46
    POSITIVE LOGITS
    NOPQRST
    0.58
     severally
    0.57
    Personendaten
    0.53
    Demografía
    0.52
    Breite
    0.51
    äsident
    0.50
    prefixer
    0.50
     tôt
    0.49
     abstrato
    0.49
    씩
    0.48
    Activations Density 4.802%

    No Known Activations