© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12173
    Prev
    Next
    INDEX
    Explanations

    words associated with media, entertainment programs, and/or nationalities

    oai_token-act-pair · gemini-2.0-flash

    television programs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IsContent
    -0.76
    ⓧ
    -0.73
     utafitiHapana
    -0.72
    RegressionTest
    -0.70
    ValueStyle
    -0.68
    MessageTagHelper
    -0.65
    processable
    -0.63
    données
    -0.62
    UnusedPrivate
    -0.59
     Halley
    -0.59
    POSITIVE LOGITS
     referenties
    0.44
     Sof
    0.43
     sof
    0.43
    hl
    0.42
    lhes
    0.42
    たまたま
    0.42
     tarto
    0.41
    htë
    0.41
     s
    0.41
    dra
    0.40
    Activations Density 1.229%

    No Known Activations