© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4791
    Prev
    Next
    INDEX
    Explanations

    movie or TV show information, frequently identifying actors and roles

    oai_token-act-pair · gemini-2.0-flash

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     kasarigan
    -0.77
    ineno
    -0.55
    HasForeignKey
    -0.55
     disponibilités
    -0.53
     SYLLABLE
    -0.52
    AndroidJUnit
    -0.52
    orianCalendar
    -0.52
     ***!
    -0.52
     KeyError
    -0.51
    UnifiedTopology
    -0.51
    POSITIVE LOGITS
     AssemblyCompany
    0.54
    StoreMessageInfo
    0.51
    //
    0.49
     MonoBehaviour
    0.48
    ]")]
    0.46
    ̣n
    0.46
     Tapes
    0.43
     Numerade
    0.42
    ادث
    0.42
    είο
    0.41
    Activations Density 1.649%

    No Known Activations