© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8297
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in business presentations and marketing

    oai_token-act-pair · gemini-2.0-flash

    room

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    mergeFrom
    -0.64
    WebElementEntity
    -0.63
    VIAF
    -0.61
     >=",
    -0.58
    MigrationBuilder
    -0.58
     typelib
    -0.57
    tvguidetime
    -0.57
    HomeAsUpEnabled
    -0.56
    ientôt
    -0.55
    featureID
    -0.55
    POSITIVE LOGITS
     room
    1.66
     Room
    1.38
    room
    1.36
    Room
    1.32
     audience
    1.26
     ROOM
    1.25
     crowd
    1.08
    ROOM
    1.08
     rooms
    1.04
     Raum
    1.02
    Activations Density 0.933%

    No Known Activations